© 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. 125401
    Prev
    Next
    INDEX
    Explanations

    phrases indicating employment or work relationships

    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
    iloc
    -0.07
    inges
    -0.07
    angu
    -0.07
    FormField
    -0.06
    SEX
    -0.06
    elle
    -0.06
    amac
    -0.06
    KeySpec
    -0.06
    nis
    -0.06
    dice
    -0.06
    POSITIVE LOGITS
    agrid
    0.08
    ussy
    0.07
    flare
    0.06
     Causes
    0.06
    entar
    0.06
    edral
    0.06
    grese
    0.06
    kl
    0.06
    antas
    0.06
    swith
    0.06
    Activations Density 0.014%

    No Known Activations