© 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. 126431
    Prev
    Next
    INDEX
    Explanations

    quotation marks and apostrophes in the text

    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
    ProcessEvent
    -0.07
    Īĺ
    -0.07
    bakan
    -0.07
    #__
    -0.07
    ActionResult
    -0.07
    ernet
    -0.06
    _registro
    -0.06
    ãĥ¼ãĥį
    -0.06
    ÐłÐĺ
    -0.06
    ãĥŃãĥ¼
    -0.06
    POSITIVE LOGITS
    olen
    0.06
    berg
    0.06
    aram
    0.06
    rm
    0.05
    gabe
    0.05
     Rational
    0.05
    raith
    0.05
    otton
    0.05
    oulder
    0.05
     Erg
    0.05
    Activations Density 0.008%

    No Known Activations