© 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. 17-LLAMASCOPE-RES-131K
    11. 87188
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" or phrases including it

    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
    èį
    -0.07
    obb
    -0.07
    vang
    -0.07
    oss
    -0.07
    ÑĢеб
    -0.06
    ENU
    -0.06
    enu
    -0.06
    ãĥ³ãĥĦ
    -0.06
    adas
    -0.06
    _FRONT
    -0.06
    POSITIVE LOGITS
     course
    0.09
    course
    0.07
    opi
    0.07
    tti
    0.07
     necessity
    0.07
    ahoma
    0.07
     whom
    0.06
    oplast
    0.06
    atatype
    0.06
    icers
    0.06
    Activations Density 0.020%

    No Known Activations