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

    Neuronpedia

    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. 39690
    Prev
    Next
    INDEX
    Explanations

    words indicating dialogue or responses

    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
    conc
    -0.07
    lien
    -0.07
    ib
    -0.07
    MOTE
    -0.06
    assage
    -0.06
    okens
    -0.06
    avy
    -0.06
    lop
    -0.06
    psz
    -0.06
    ¾
    -0.06
    POSITIVE LOGITS
    porte
    0.07
     Pell
    0.07
    _hi
    0.06
     rằng
    0.06
     Canter
    0.06
    odelist
    0.06
     that
    0.06
    WithError
    0.06
     with
    0.06
    .gms
    0.06
    Activations Density 0.008%

    No Known Activations