© 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. 15-LLAMASCOPE-RES-131K
    11. 90169
    Prev
    Next
    INDEX
    Explanations

    colons that indicate the start of a new segment or section in the text

    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
    iej
    -0.06
    ovo
    -0.06
    qry
    -0.06
    uko
    -0.06
     author
    -0.06
    инг
    -0.06
     ilk
    -0.06
    eldo
    -0.05
    elho
    -0.05
    Ùī
    -0.05
    POSITIVE LOGITS
    zell
    0.07
    /Dk
    0.07
    duk
    0.07
    bestos
    0.07
    967
    0.07
    930
    0.07
    ulses
    0.07
     tolua
    0.07
     Sahara
    0.07
    ädchen
    0.07
    Activations Density 0.001%

    No Known Activations