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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-LLAMASCOPE-RES-131K
    6. 5309
    Prev
    Next
    INDEX
    Explanations

    performance metrics and specifications related to vehicles

    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
     priv
    -0.06
     Fare
    -0.06
     ind
    -0.06
    arkin
    -0.06
    less
    -0.06
     Ko
    -0.06
     Hil
    -0.06
    idge
    -0.06
     pumped
    -0.06
    ano
    -0.06
    POSITIVE LOGITS
     mph
    0.09
    DEX
    0.09
     MPH
    0.08
     acceleration
    0.08
     accel
    0.07
     à¤Ĺत
    0.07
    achen
    0.07
    ergency
    0.07
    .Speed
    0.07
    _tac
    0.07
    Activations Density 0.002%

    No Known Activations