© 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. 126113
    Prev
    Next
    INDEX
    Explanations

    patterns related to string delimiters and punctuation in code

    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
    ½
    -0.06
     Hanson
    -0.06
     fin
    -0.06
    ual
    -0.06
     sign
    -0.05
    875
    -0.05
    DCF
    -0.05
    uf
    -0.05
    _Free
    -0.05
    _Query
    -0.05
    POSITIVE LOGITS
    endcode
    0.07
    ган
    0.07
    umlu
    0.07
    zı
    0.07
    arna
    0.07
    ı
    0.07
    irse
    0.07
    Tar
    0.07
    pector
    0.06
    cg
    0.06
    Activations Density 0.065%

    No Known Activations