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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 29-LLAMASCOPE-RES-32K
    11. 3424
    Prev
    Next
    INDEX
    Explanations

    phrases related to health risks and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dol
    -0.15
    472
    -0.14
    æ²»çĸĹ
    -0.14
    ATUS
    -0.14
     Treatment
    -0.14
     treatment
    -0.13
    udos
    -0.13
     chaud
    -0.13
    PLIT
    -0.13
    endoza
    -0.13
    POSITIVE LOGITS
     developing
    0.32
     Developing
    0.28
     develop
    0.26
     development
    0.26
     contracting
    0.25
    develop
    0.24
     develops
    0.24
     devel
    0.24
     DEVELO
    0.23
     strokes
    0.23
    Activations Density 0.140%

    No Known Activations