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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 96142
    Prev
    Next
    INDEX
    Explanations

    phrases concerning scientific methodologies and achievements

    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
    lse
    -0.07
    ãĥ¼ãĤ¯
    -0.06
    less
    -0.06
    ç´
    -0.06
    emin
    -0.06
    _SEL
    -0.06
    ns
    -0.06
    ing
    -0.06
    train
    -0.06
     sert
    -0.06
    POSITIVE LOGITS
    rette
    0.08
    otte
    0.08
    abela
    0.08
    urette
    0.07
    .scalablytyped
    0.07
    olate
    0.07
    ellite
    0.07
    ÐIJÑĢÑħÑĸв
    0.07
    )((((
    0.06
    Reducers
    0.06
    Activations Density 0.288%

    No Known Activations