© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27339
    Prev
    Next
    INDEX
    Explanations

    comparative phrases highlighting contrasts between subjects

    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
    ossal
    -0.06
     Ronald
    -0.06
    ullo
    -0.06
    ooke
    -0.05
     Wright
    -0.05
     Roch
    -0.05
    ebe
    -0.05
    anning
    -0.05
    аннÑĭ
    -0.05
    chrift
    -0.05
    POSITIVE LOGITS
    öz
    0.08
    DATES
    0.08
    odia
    0.08
    akit
    0.07
    outil
    0.07
    omorphic
    0.07
     Cunning
    0.07
    ìŀ¥ìĿĢ
    0.07
    whose
    0.07
    rowsing
    0.07
    Activations Density 0.009%

    No Known Activations