© 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. 84607
    Prev
    Next
    INDEX
    Explanations

    generic qualifiers that indicate non-specificity or inclusivity

    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
    arel
    -0.07
    enaire
    -0.07
    aldi
    -0.06
    èĪ
    -0.06
    kaar
    -0.06
    aut
    -0.06
     pl
    -0.06
    enia
    -0.06
     NEC
    -0.06
    ãģ¡ãģ¯
    -0.06
    POSITIVE LOGITS
    Triangles
    0.07
    Bron
    0.07
    ocab
    0.06
    elm
    0.06
    orte
    0.06
     blot
    0.06
    ocz
    0.06
    oliday
    0.06
    tes
    0.06
     blame
    0.06
    Activations Density 0.001%

    No Known Activations