Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95965
    Prev
    Next
    INDEX
    Explanations

    words relating to advantages and beneficial aspects of something

    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
    .GetBytes
    -0.07
    inch
    -0.07
    krom
    -0.06
    oš
    -0.06
    wap
    -0.06
    омеÑĤ
    -0.06
    izar
    -0.06
    voke
    -0.06
     Trot
    -0.06
    array
    -0.06
    POSITIVE LOGITS
    ulen
    0.07
    ieri
    0.06
    eyJ
    0.06
    ÙĬÙĦا
    0.06
    uele
    0.06
    rypton
    0.06
     yg
    0.06
    riet
    0.06
    iyas
    0.06
    ehir
    0.06
    Activations Density 0.000%

    No Known Activations