© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86039
    Prev
    Next
    INDEX
    Explanations

    phrases or constructs that begin with "over" or "out"

    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
    enance
    -0.07
    swer
    -0.07
    561
    -0.06
    ccion
    -0.06
    ething
    -0.06
    ponent
    -0.06
    zz
    -0.06
    620
    -0.06
    üp
    -0.06
    plevel
    -0.06
    POSITIVE LOGITS
    лам
    0.08
    -valu
    0.08
    eyJ
    0.07
    /Branch
    0.07
     planetary
    0.07
    SURE
    0.07
    onda
    0.07
    habi
    0.07
    OME
    0.07
    esser
    0.06
    Activations Density 0.022%

    No Known Activations