© 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. 17-LLAMASCOPE-RES-131K
    11. 56316
    Prev
    Next
    INDEX
    Explanations

    instances of joining or entering organizations or groups

    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
    nis
    -0.07
    CONF
    -0.06
    estival
    -0.06
    rå
    -0.06
    .setResult
    -0.06
    oud
    -0.06
    versible
    -0.06
    ideographic
    -0.06
    _TIMES
    -0.06
    rect
    -0.06
    POSITIVE LOGITS
    appa
    0.08
     onto
    0.08
     into
    0.07
    tright
    0.07
     newly
    0.07
    into
    0.07
     Into
    0.06
    ikip
    0.06
    620
    0.06
     adultes
    0.06
    Activations Density 0.017%

    No Known Activations