© 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. 61349
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas

    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
    VILLE
    -0.06
    fatal
    -0.06
    ismet
    -0.06
    xd
    -0.06
    ordial
    -0.06
    apture
    -0.06
    .Net
    -0.06
    kup
    -0.06
    EDURE
    -0.06
    avadoc
    -0.06
    POSITIVE LOGITS
    vern
    0.07
    ehr
    0.07
    dealloc
    0.06
    efa
    0.06
     Conway
    0.06
    rian
    0.06
    jeta
    0.06
    گاب
    0.06
     ;č↵
    0.06
    éĽħ
    0.06
    Activations Density 0.136%

    No Known Activations