© 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. 125281
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating purpose or intention

    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
    ooter
    -0.07
    porno
    -0.06
     sort
    -0.06
    819
    -0.06
    rend
    -0.05
     Chapman
    -0.05
     tail
    -0.05
    âĢ
    -0.05
    вÑĸ
    -0.05
    .neg
    -0.05
    POSITIVE LOGITS
     tôi
    0.08
     me
    0.08
    ollo
    0.07
    eyer
    0.07
    ActionCreators
    0.07
    icator
    0.07
     authorities
    0.07
    sockopt
    0.07
    oldt
    0.07
     him
    0.07
    Activations Density 0.044%

    No Known Activations