© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 105997
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate movement or action through space

    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
     addCriterion
    -0.08
    edom
    -0.08
    #
    -0.07
    .scalablytyped
    -0.07
    "';
    -0.07
    .IsNullOr
    -0.07
    urum
    -0.07
    à¸²à¸ł
    -0.07
    à¸Ĺย
    -0.07
     cref
    -0.07
    POSITIVE LOGITS
    asse
    0.06
     Bloody
    0.06
    ort
    0.06
    ik
    0.06
    ãĥ¼ãĥª
    0.06
     duties
    0.06
    ics
    0.06
    esin
    0.06
    quette
    0.06
     with
    0.06
    Activations Density 0.095%

    No Known Activations