© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78111
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and structures

    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
     reform
    -0.07
    ree
    -0.07
    ather
    -0.06
    ¿
    -0.06
    erm
    -0.06
    çĥ
    -0.06
    ometown
    -0.06
    -transform
    -0.06
    311
    -0.06
    846
    -0.06
    POSITIVE LOGITS
     gloss
    0.08
    imu
    0.07
    doch
    0.07
    ï¼³
    0.07
    hores
    0.06
    .codes
    0.06
     Gloss
    0.06
     Dude
    0.06
    оÑĢо
    0.06
     Ridley
    0.06
    Activations Density 0.006%

    No Known Activations