© 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. 16697
    Prev
    Next
    INDEX
    Explanations

    organizational or structural aspects of cultural or artistic expressions

    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
     Dex
    -0.06
    yled
    -0.06
     SAF
    -0.06
    ighth
    -0.06
    dy
    -0.05
    ses
    -0.05
    orca
    -0.05
    ẩy
    -0.05
    ,},↵
    -0.05
     åĤ
    -0.05
    POSITIVE LOGITS
    kili
    0.08
    istra
    0.07
    opr
    0.07
    lak
    0.07
    vak
    0.07
    ÏĮγ
    0.07
    contri
    0.06
    rve
    0.06
    Å¡il
    0.06
    Mutable
    0.06
    Activations Density 0.008%

    No Known Activations