© 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. 129016
    Prev
    Next
    INDEX
    Explanations

    a specific character or symbol representation 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
    s
    -0.08
    >NN
    -0.07
    sar
    -0.07
    edelta
    -0.07
    099
    -0.07
    arsity
    -0.07
    phies
    -0.07
    oval
    -0.07
    opolitan
    -0.07
    acters
    -0.06
    POSITIVE LOGITS
     glare
    0.07
    vig
    0.06
    ASF
    0.06
    vik
    0.06
    ä½ı
    0.06
    getc
    0.06
    raki
    0.06
    Ñīа
    0.06
    _cre
    0.06
    ball
    0.06
    Activations Density 0.001%

    No Known Activations