© 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 EvalsExportsinterp-engineNEWAPI 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. 14914
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names, often associated with artistic or historical context

    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
    .ms
    -0.09
    ollectors
    -0.09
    gregar
    -0.08
    ÙģتÙħ
    -0.08
    ndef
    -0.08
    ROTO
    -0.08
    plevel
    -0.08
    ezi
    -0.08
    pline
    -0.08
    sse
    -0.08
    POSITIVE LOGITS
    âĢħ
    0.06
    0.06
    Âł
    0.06
    ↵
    0.06
     âĢ¦
    0.06
    âĢ¦
    0.05
    [âĢ¦]
    0.05
     Ark
    0.05
     [âĢ¦]
    0.05
    ahir
    0.05
    Activations Density 0.066%

    No Known Activations