© 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. 61380
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and code syntax elements

    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
    oha
    -0.07
    ¶Į
    -0.07
     opak
    -0.07
    anglicky
    -0.07
    _$_
    -0.06
    emente
    -0.06
    Ä°Y
    -0.06
    ç»ĻæĪij
    -0.06
    "struct
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    POSITIVE LOGITS
    ote
    0.07
    uel
    0.07
     Sage
    0.06
    esser
    0.06
     Wor
    0.06
    fare
    0.06
    erc
    0.06
    ati
    0.06
    amilia
    0.06
    worthy
    0.06
    Activations Density 0.238%

    No Known Activations