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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 60947
    Prev
    Next
    INDEX
    Explanations

    references to data analysis techniques and processes in research

    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
    owie
    -0.07
    owan
    -0.06
     [+
    -0.06
    lettes
    -0.06
     attention
    -0.06
    bling
    -0.06
     ucwords
    -0.06
     Bits
    -0.06
     refreshing
    -0.06
     outside
    -0.05
    POSITIVE LOGITS
     data
    0.15
    data
    0.12
     raw
    0.12
    æķ°æį®
    0.11
    raw
    0.10
    /raw
    0.10
    -data
    0.10
    ãĥĩãĥ¼ãĤ¿
    0.10
     collected
    0.10
     даннÑĭÑħ
    0.09
    Activations Density 0.094%

    No Known Activations