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. 16410
    Prev
    Next
    INDEX
    Explanations

    references to numerical or coded data

    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
    ento
    -0.07
    ugal
    -0.06
    hog
    -0.06
    769
    -0.06
    aby
    -0.06
     dra
    -0.06
     commun
    -0.06
    ategorized
    -0.05
    set
    -0.05
    en
    -0.05
    POSITIVE LOGITS
    OKIE
    0.08
    jos
    0.08
    EEP
    0.07
    ocu
    0.07
     Eaton
    0.07
    #echo
    0.07
    ddl
    0.07
    éı¡
    0.07
    WISE
    0.07
    allel
    0.07
    Activations Density 0.003%

    No Known Activations