© 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. 126267
    Prev
    Next
    INDEX
    Explanations

    references to legal or licensing details regarding content or source code

    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
    biz
    -0.07
    agg
    -0.07
    wire
    -0.06
    bmp
    -0.06
    ather
    -0.06
    ashi
    -0.06
     Dra
    -0.06
    ÑģÑĤеÑĢ
    -0.06
    ows
    -0.05
    å¼
    -0.05
    POSITIVE LOGITS
    تÙĥ
    0.07
     Nose
    0.06
    thood
    0.06
    eya
    0.06
    ByUrl
    0.06
    ilage
    0.06
    uma
    0.06
    еÑĢеж
    0.06
    _pdata
    0.06
     kvin
    0.06
    Activations Density 0.001%

    No Known Activations