© 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. 5-LLAMASCOPE-RES-131K
    11. 125907
    Prev
    Next
    INDEX
    Explanations

    expressions of purpose or intent

    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
    å¹¹ç·ļ
    -0.07
    kil
    -0.07
    amac
    -0.07
    ilate
    -0.07
    andon
    -0.07
    atur
    -0.07
    elage
    -0.06
     nues
    -0.06
     zf
    -0.06
    ноз
    -0.06
    POSITIVE LOGITS
    ible
    0.07
    λικ
    0.06
    716
    0.06
    .absolute
    0.06
    bie
    0.06
    /by
    0.05
    licable
    0.05
    684
    0.05
    astic
    0.05
    able
    0.05
    Activations Density 0.001%

    No Known Activations