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. 96210
    Prev
    Next
    INDEX
    Explanations

    phrases related to troubleshooting and technical problem-solving

    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
    adla
    -0.07
    ngrx
    -0.07
    妮
    -0.07
    (STD
    -0.07
    æĥħ
    -0.06
    subtype
    -0.06
    bay
    -0.06
    dre
    -0.06
    omit
    -0.06
    prd
    -0.06
    POSITIVE LOGITS
     célib
    0.07
     Stam
    0.07
     Tie
    0.06
     Vine
    0.06
    ime
    0.06
     ninete
    0.06
    _simps
    0.05
    äche
    0.05
    .Cookies
    0.05
    108
    0.05
    Activations Density 0.044%

    No Known Activations