© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71138
    Prev
    Next
    INDEX
    Explanations

    references to human cells or biological research involving humans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igel
    -0.07
    گاÙĩ
    -0.06
    elia
    -0.06
    ennis
    -0.06
     nhau
    -0.06
    WithOptions
    -0.06
    adlo
    -0.06
     fellow
    -0.06
    ulary
    -0.06
    nh
    -0.06
    POSITIVE LOGITS
    izzle
    0.07
    IFY
    0.07
    -specific
    0.07
    ãĥ¬ãĥĥãĥĪ
    0.07
    -Russian
    0.07
    ëĭµ
    0.06
    preg
    0.06
    -origin
    0.06
    -wide
    0.06
    .permission
    0.06
    Activations Density 0.018%

    No Known Activations