© 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. 106777
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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
    esser
    -0.07
    orks
    -0.07
    ÑĦоÑĢми
    -0.07
    çݲ
    -0.06
     Pediatrics
    -0.06
    ownik
    -0.06
     geil
    -0.06
    licit
    -0.06
    UrlParser
    -0.06
    ãĥŃãĥ¼
    -0.06
    POSITIVE LOGITS
    ãģıãĤī
    0.07
    chedulers
    0.07
     Stall
    0.06
    usch
    0.06
    \-
    0.06
    aza
    0.06
    hq
    0.06
    BCM
    0.06
    ahat
    0.06
    STALL
    0.06
    Activations Density 0.000%

    No Known Activations