© 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. 93613
    Prev
    Next
    INDEX
    Explanations

    issues related to social or economic disparity

    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
    ãģķãģ¾
    -0.08
    iges
    -0.07
    /renderer
    -0.07
     Agricult
    -0.07
    slash
    -0.07
    dra
    -0.07
    uhe
    -0.07
    kla
    -0.07
    antino
    -0.07
    nid
    -0.07
    POSITIVE LOGITS
     publicly
    0.06
     incompatible
    0.06
     LAP
    0.06
    oriously
    0.06
     consistent
    0.06
     compatible
    0.06
     existing
    0.06
    âģ
    0.05
     public
    0.05
     retrofit
    0.05
    Activations Density 0.000%

    No Known Activations