Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96108
    Prev
    Next
    INDEX
    Explanations

    elements related to educational training and programs

    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
    .her
    -0.08
    esel
    -0.07
    eldom
    -0.07
    UNS
    -0.07
    postalcode
    -0.07
    oplay
    -0.07
    strom
    -0.07
    oha
    -0.06
    iglia
    -0.06
    uisine
    -0.06
    POSITIVE LOGITS
    veau
    0.07
     Bulk
    0.06
    648
    0.06
    otel
    0.06
    oyal
    0.06
    rance
    0.06
     Loving
    0.05
    ilis
    0.05
     occupants
    0.05
    _Generic
    0.05
    Activations Density 0.010%

    No Known Activations