Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40411
    Prev
    Next
    INDEX
    Explanations

    curly braces and return statements 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
    hood
    -0.07
    burn
    -0.06
    arger
    -0.06
    hs
    -0.06
    ester
    -0.06
    jl
    -0.06
    quared
    -0.06
    i
    -0.06
     types
    -0.06
    lace
    -0.06
    POSITIVE LOGITS
    atk
    0.08
     Atlas
    0.07
    ixmap
    0.07
     поба
    0.07
    Atlas
    0.07
    asher
    0.07
    "value
    0.07
     INLINE
    0.07
    vanced
    0.07
     голови
    0.07
    Activations Density 0.003%

    No Known Activations