© 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. 29642
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and regional identities

    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
    olon
    -0.08
    galement
    -0.08
    OPY
    -0.08
    illez
    -0.08
    iverz
    -0.08
    UrlParser
    -0.08
    razione
    -0.08
    Languages
    -0.07
    ibName
    -0.07
    .truth
    -0.07
    POSITIVE LOGITS
     citizens
    0.08
    ian
    0.07
     people
    0.07
     citizen
    0.07
    ians
    0.06
     folk
    0.06
    rs
    0.06
    /Set
    0.06
     residents
    0.06
    ers
    0.06
    Activations Density 0.024%

    No Known Activations