© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    references to package names and class imports from Java or similar programming languages

    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
    raya
    -0.08
    insky
    -0.08
    ernaut
    -0.08
    harma
    -0.08
    .bootstrapcdn
    -0.08
    insk
    -0.08
    ricks
    -0.07
    SHOT
    -0.07
    leine
    -0.07
    esk
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.11
     Ballard
    0.06
    str
    0.06
     تس
    0.05
     Linux
    0.05
     æ
    0.05
    s
    0.05
    sense
    0.05
    .function
    0.05
     Basil
    0.05
    Activations Density 0.001%

    No Known Activations