© 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. 77412
    Prev
    Next
    INDEX
    Explanations

    HTTP headers and content type references

    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
    ulo
    -0.07
     Fowler
    -0.07
    ulet
    -0.06
    éĽĨä¸Ń
    -0.06
    ',{'
    -0.06
    icious
    -0.06
    olo
    -0.06
    rien
    -0.06
    oeff
    -0.06
    ije
    -0.06
    POSITIVE LOGITS
    osu
    0.07
    Scope
    0.07
    Source
    0.07
    _inches
    0.07
    TY
    0.07
     tarz
    0.06
    ears
    0.06
    density
    0.06
    IAL
    0.06
    warz
    0.06
    Activations Density 0.002%

    No Known Activations