© 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. 118440
    Prev
    Next
    INDEX
    Explanations

    geographical locations and references to various places

    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
    [âĢ¦
    -0.06
    ť
    -0.06
    riz
    -0.06
     defaultCenter
    -0.06
    éĻ
    -0.06
    éħ
    -0.06
    acos
    -0.06
     mined
    -0.06
    URLConnection
    -0.06
    arium
    -0.06
    POSITIVE LOGITS
     who
    0.09
    who
    0.07
     are
    0.07
    ady
    0.07
    embro
    0.07
    .vertx
    0.06
    atan
    0.06
    olf
    0.06
    toy
    0.06
    .mybatisplus
    0.06
    Activations Density 0.033%

    No Known Activations