© 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. 22-LLAMASCOPE-RES-131K
    6. 4063
    Prev
    Next
    INDEX
    Explanations

    references to individuals or organizations giving endorsements or donations

    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
    airo
    -0.07
    oso
    -0.06
     norge
    -0.06
    ulur
    -0.06
    air
    -0.06
     IGN
    -0.06
     Campos
    -0.05
    Ĥæķ°
    -0.05
    aisy
    -0.05
    \ORM
    -0.05
    POSITIVE LOGITS
     Whe
    0.08
     )↵↵↵↵↵↵↵↵
    0.07
    uron
    0.07
    ez
    0.07
    zcze
    0.07
     Hra
    0.07
     entitled
    0.06
    ÑĦÑĤ
    0.06
    ori
    0.06
    eid
    0.06
    Activations Density 0.004%

    No Known Activations