© 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. 126456
    Prev
    Next
    INDEX
    Explanations

    instructions and requirements for submissions and applications

    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
     bra
    -0.06
     fund
    -0.06
    ailable
    -0.06
    kad
    -0.06
    eten
    -0.06
    ãĥ¼ãĥģ
    -0.06
    uras
    -0.06
    asil
    -0.06
    á»ĵng
    -0.06
    ilet
    -0.06
    POSITIVE LOGITS
    _unregister
    0.08
    ivant
    0.08
    aal
    0.07
    reta
    0.07
     Fletcher
    0.06
    樹
    0.06
    -basket
    0.06
    ÅĻÃŃz
    0.06
     entreg
    0.06
    åĩĢ
    0.06
    Activations Density 0.007%

    No Known Activations