© 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. 126223
    Prev
    Next
    INDEX
    Explanations

    phrases associated with dependence and reliance

    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
     Lawson
    -0.08
    orp
    -0.07
    anou
    -0.07
    amon
    -0.07
    lee
    -0.07
    agal
    -0.07
    èĬ
    -0.07
    mant
    -0.07
    inez
    -0.07
    ë§Ŀ
    -0.07
    POSITIVE LOGITS
     upon
    0.09
    oty
    0.08
    ingly
    0.07
    857
    0.07
     heavily
    0.07
    antly
    0.07
    <|begin_of_text|>
    0.07
    è°±
    0.06
    lessly
    0.06
     Upon
    0.06
    Activations Density 0.008%

    No Known Activations