© 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. 17-LLAMASCOPE-RES-131K
    6. 83049
    Prev
    Next
    INDEX
    Explanations

    trademarked symbols or terms indicating proprietary products or features

    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
    iferay
    -0.08
    guard
    -0.08
    ses
    -0.08
    ORIZONTAL
    -0.08
    /or
    -0.08
    enti
    -0.08
    bang
    -0.07
    /her
    -0.07
    ie
    -0.07
    ings
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.21
    ï¸
    0.10
    gether
    0.07
    iž
    0.07
    ing
    0.06
    Unavailable
    0.06
    /-
    0.06
    raries
    0.06
    ehler
    0.06
    oriously
    0.06
    Activations Density 0.006%

    No Known Activations