© 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. 31-LLAMASCOPE-RES-32K
    11. 10381
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to liver health and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itt
    -0.37
    ett
    -0.36
    ITT
    -0.36
    atti
    -0.36
    OTT
    -0.36
    ãĥĥ
    -0.34
    utt
    -0.34
    itti
    -0.33
    ATT
    -0.33
    ette
    -0.32
    POSITIVE LOGITS
    ¬ģ
    0.15
    ¬Ĥ
    0.14
    licant
    0.12
    286
    0.12
    ospace
    0.12
     apis
    0.12
    caler
    0.12
    osate
    0.11
    iangle
    0.11
    625
    0.11
    Activations Density 0.361%

    No Known Activations