© 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. 55829
    Prev
    Next
    INDEX
    Explanations

    positive descriptions and expressions of involvement in community or collaborative events

    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
    ascus
    -0.08
    upos
    -0.07
    arend
    -0.07
    dál
    -0.07
    andler
    -0.07
    Squared
    -0.07
    aversal
    -0.07
    asz
    -0.06
    isman
    -0.06
    .Accessible
    -0.06
    POSITIVE LOGITS
    urer
    0.07
     partnership
    0.07
     participation
    0.06
     contribution
    0.06
     Join
    0.06
    support
    0.06
     joins
    0.06
     join
    0.06
     hoping
    0.06
     supports
    0.06
    Activations Density 0.018%

    No Known Activations