© 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. 57165
    Prev
    Next
    INDEX
    Explanations

    HTML form actions and methods

    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
     ÑĤоÑĢ
    -0.06
    optera
    -0.06
     Roll
    -0.06
    ppo
    -0.06
     propos
    -0.06
     preparations
    -0.06
     <$>
    -0.06
    ollision
    -0.05
     vict
    -0.05
     repe
    -0.05
    POSITIVE LOGITS
    enson
    0.08
    itan
    0.08
    hdl
    0.08
    blank
    0.07
    outh
    0.07
    than
    0.07
     puta
    0.07
     blanco
    0.07
    =sys
    0.07
    resse
    0.07
    Activations Density 0.001%

    No Known Activations