© 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. 86170
    Prev
    Next
    INDEX
    Explanations

    references to discussions or exchanges between individuals

    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
    edir
    -0.08
    éri
    -0.07
    emain
    -0.07
    λοι
    -0.07
    _codec
    -0.07
     cÆ°á»Ŀi
    -0.07
    ÙĦÙĬÙĩ
    -0.07
    /inet
    -0.07
     bä
    -0.07
    &S
    -0.07
    POSITIVE LOGITS
     said
    0.07
     pref
    0.07
     asked
    0.07
     Said
    0.07
     ask
    0.07
    imir
    0.06
     saying
    0.06
     remark
    0.06
    ook
    0.06
    ettle
    0.06
    Activations Density 0.045%

    No Known Activations