© 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. 9-LLAMASCOPE-RES-131K
    11. 95695
    Prev
    Next
    INDEX
    Explanations

    technical and programming-related terms or identifiers

    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
    thal
    -0.08
    ovi
    -0.07
    iverz
    -0.07
    елиÑĩ
    -0.07
    ystick
    -0.07
    elt
    -0.07
    elda
    -0.07
    rgan
    -0.07
    raç
    -0.07
    +-+-+-+-
    -0.07
    POSITIVE LOGITS
    etimes
    0.06
     Included
    0.06
     Kum
    0.06
     Ent
    0.06
     Inside
    0.05
     Vick
    0.05
    Ess
    0.05
    عب
    0.05
    dojo
    0.05
     Hel
    0.05
    Activations Density 0.002%

    No Known Activations