© 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. 93972
    Prev
    Next
    INDEX
    Explanations

    layout specifications and attributes in coding or markup languages

    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
    onto
    -0.07
    ordes
    -0.07
    ovol
    -0.07
    incinn
    -0.07
    igli
    -0.07
    gni
    -0.06
     Helmet
    -0.06
    fc
    -0.06
    виÑĩ
    -0.06
    unto
    -0.06
    POSITIVE LOGITS
    zers
    0.07
    526
    0.07
    576
    0.06
    zar
    0.06
    ussen
    0.06
    758
    0.06
    ancestor
    0.06
    ìĭ±
    0.06
    arians
    0.05
    307
    0.05
    Activations Density 0.000%

    No Known Activations