© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 28705
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and health conditions, particularly in the context of treatments and their potential effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    коÑĤ
    -0.14
     suicidal
    -0.14
    acin
    -0.14
    ERO
    -0.13
    inh
    -0.13
     schizophren
    -0.13
     Suicide
    -0.13
     Swift
    -0.13
    kın
    -0.13
     suicide
    -0.13
    POSITIVE LOGITS
     condition
    0.57
     conditions
    0.54
     Conditions
    0.48
     Condition
    0.47
    conditions
    0.45
    condition
    0.43
     disorder
    0.43
     disorders
    0.42
    Condition
    0.41
    Conditions
    0.41
    Activations Density 0.280%

    No Known Activations