Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96203
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting notations in 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
    habi
    -0.08
     Singular
    -0.07
    zdy
    -0.06
    ossip
    -0.06
    HEMA
    -0.06
    pite
    -0.06
    jde
    -0.06
    onia
    -0.06
    ategy
    -0.06
     humble
    -0.06
    POSITIVE LOGITS
    ÑĨик
    0.07
    ("(%
    0.06
     Ñģви
    0.06
     Grü
    0.06
     zlat
    0.06
    Ð¡Ðł
    0.06
    .backward
    0.06
    æŃ
    0.06
     sca
    0.06
     exem
    0.06
    Activations Density 0.000%

    No Known Activations