© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 59290
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their associated contexts related to physical objects and actions

    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
    ÙĬÙĦاد
    -0.08
    .integration
    -0.08
     Bilim
    -0.08
    ivec
    -0.08
    cak
    -0.08
    ussen
    -0.08
    _________________↵↵
    -0.08
    Misc
    -0.08
    misc
    -0.08
    EIF
    -0.08
    POSITIVE LOGITS
    less
    0.07
    -less
    0.06
    ess
    0.06
    (s
    0.06
    ilt
    0.05
     always
    0.05
    lessness
    0.05
    âĢ¦↵
    0.05
    ê
    0.05
    lexer
    0.05
    Activations Density 0.048%

    No Known Activations