© 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. 76856
    Prev
    Next
    INDEX
    Explanations

    references to community and support for vulnerable populations

    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
    idor
    -0.07
    ont
    -0.07
    eca
    -0.07
    alo
    -0.07
    aget
    -0.07
    anten
    -0.06
    ries
    -0.06
    iste
    -0.06
    .Extensions
    -0.06
     pog
    -0.06
    POSITIVE LOGITS
    ofile
    0.07
     nation
    0.07
     communities
    0.07
    stored
    0.06
     all
    0.06
    Ñīей
    0.06
    ìķ½
    0.06
    един
    0.06
    ancode
    0.06
     à¤ķरव
    0.06
    Activations Density 0.017%

    No Known Activations