© 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. 93550
    Prev
    Next
    INDEX
    Explanations

    expressions of amazement or surprise

    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
    yll
    -0.07
    idl
    -0.06
    iggs
    -0.06
    avou
    -0.06
    ucker
    -0.06
    .scalablytyped
    -0.06
    sez
    -0.06
    uir
    -0.06
    ç§ĭ
    -0.06
    ugg
    -0.06
    POSITIVE LOGITS
    za
    0.09
     fadeIn
    0.08
    tility
    0.07
    INGTON
    0.07
    ington
    0.07
    ingly
    0.07
    zers
    0.07
    rhs
    0.07
     RHS
    0.07
    chemy
    0.07
    Activations Density 0.003%

    No Known Activations