© 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. 119501
    Prev
    Next
    INDEX
    Explanations

    references to events or actions that include involvement or participation in incidents or situations

    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
    .dateTime
    -0.07
    quila
    -0.07
    csi
    -0.07
    ãĥĨãĥ«
    -0.07
    .fromString
    -0.07
    .createClass
    -0.07
    oster
    -0.07
    STYPE
    -0.07
     Grass
    -0.07
    abel
    -0.07
    POSITIVE LOGITS
    827
    0.09
    hani
    0.07
    lage
    0.07
    hra
    0.07
    akra
    0.07
    .
    0.06
    /by
    0.06
    127
    0.06
    antz
    0.06
    922
    0.06
    Activations Density 0.009%

    No Known Activations