© 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. 40307
    Prev
    Next
    INDEX
    Explanations

    references to causation or justification in explanations or arguments

    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
     mie
    -0.06
    нÑĮ
    -0.06
    orting
    -0.06
    akte
    -0.06
    akens
    -0.06
    abra
    -0.06
    _BOUNDS
    -0.06
    otify
    -0.06
     because
    -0.06
    ÑĸлÑĮ
    -0.06
    POSITIVE LOGITS
    quier
    0.07
    esser
    0.07
    }());↵
    0.06
    ewire
    0.06
    lename
    0.06
    uthor
    0.06
    .Interface
    0.06
     Hod
    0.06
    ableObject
    0.06
    /pm
    0.06
    Activations Density 0.005%

    No Known Activations