© 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. 118957
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    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
     Ruby
    -0.07
    addock
    -0.07
    elop
    -0.07
    ruby
    -0.07
    isay
    -0.06
    -scrollbar
    -0.06
    Ruby
    -0.06
     ADDRESS
    -0.06
    metic
    -0.06
    adow
    -0.06
    POSITIVE LOGITS
    ilde
    0.07
    ỡ
    0.07
    illy
    0.06
    anken
    0.06
    aniel
    0.06
    ane
    0.06
    odo
    0.06
     Shane
    0.06
    illos
    0.06
    alm
    0.06
    Activations Density 0.000%

    No Known Activations