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. 96187
    Prev
    Next
    INDEX
    Explanations

    references to memorable experiences or quotes

    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
    ent
    -0.06
    ries
    -0.06
    é£İ
    -0.06
     Pip
    -0.06
     ay
    -0.06
     Ay
    -0.06
    sections
    -0.05
    bit
    -0.05
    風
    -0.05
     coverage
    -0.05
    POSITIVE LOGITS
    ordan
    0.08
    yaw
    0.07
     Vander
    0.07
    untu
    0.07
    @js
    0.07
    otts
    0.07
    arden
    0.07
    Gesture
    0.07
    rack
    0.07
    iyon
    0.07
    Activations Density 0.135%

    No Known Activations