© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71375
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to performing actions or making choices

    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
    óng
    -0.07
    uko
    -0.07
    asio
    -0.07
    isci
    -0.07
    duk
    -0.07
    imas
    -0.07
     ----------------------------------------------------------------------------↵
    -0.07
    atts
    -0.06
    åĬªåĬĽ
    -0.06
    ahl
    -0.06
    POSITIVE LOGITS
     anymore
    0.15
     any
    0.11
     anything
    0.10
     nor
    0.10
     unless
    0.09
     nÃło
    0.09
    anything
    0.09
     ANY
    0.09
    any
    0.08
     necessarily
    0.08
    Activations Density 0.056%

    No Known Activations