© 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. 125904
    Prev
    Next
    INDEX
    Explanations

    terms emphasizing value, importance, and trust in service interactions

    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
    935
    -0.07
     Bene
    -0.07
    nde
    -0.06
    utton
    -0.06
    oir
    -0.06
    de
    -0.05
    ites
    -0.05
    695
    -0.05
    gett
    -0.05
    vn
    -0.05
    POSITIVE LOGITS
    raud
    0.08
    opa
    0.07
    yan
    0.07
     Ley
    0.07
    ledge
    0.07
    URRE
    0.07
    Äĩ
    0.07
    ibi
    0.06
    apon
    0.06
    IVAL
    0.06
    Activations Density 0.003%

    No Known Activations