© 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. 3167
    Prev
    Next
    INDEX
    Explanations

    technical specifications and methods for electronic or communication devices

    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
    regor
    -0.08
    ãĤĩ
    -0.06
    alem
    -0.06
    jist
    -0.06
    undler
    -0.06
    Ùģات
    -0.06
    .pp
    -0.06
    undo
    -0.06
    .Apis
    -0.06
    erner
    -0.06
    POSITIVE LOGITS
    eer
    0.08
    å¢
    0.07
    VERTISE
    0.06
    ĥģ
    0.06
    arg
    0.06
     geomet
    0.06
    å©
    0.06
     Ripple
    0.06
    UCT
    0.05
     STRICT
    0.05
    Activations Density 0.108%

    No Known Activations