© 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. 22-LLAMASCOPE-RES-131K
    11. 4145
    Prev
    Next
    INDEX
    Explanations

    specific terms related to food and seafood, particularly mussels

    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
    tat
    -0.07
    ulers
    -0.07
     batting
    -0.06
    orses
    -0.06
    jeme
    -0.06
    unted
    -0.06
    _bug
    -0.06
    tie
    -0.06
    rlen
    -0.06
    .rs
    -0.06
    POSITIVE LOGITS
     shells
    0.14
     shell
    0.12
    shell
    0.11
    Shell
    0.10
     Shell
    0.10
    -shell
    0.09
     moll
    0.08
    (shell
    0.08
     vá»ı
    0.08
    pir
    0.07
    Activations Density 0.002%

    No Known Activations