© 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. 9-LLAMASCOPE-RES-131K
    11. 95551
    Prev
    Next
    INDEX
    Explanations

    phrases related to diving or immersive experiences

    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
    hiro
    -0.08
    oldem
    -0.08
    .UnitTesting
    -0.07
    abis
    -0.07
    .DisplayMember
    -0.07
    rint
    -0.07
    aments
    -0.07
    ismet
    -0.07
    -sex
    -0.07
    ancell
    -0.07
    POSITIVE LOGITS
     into
    0.07
    egrator
    0.07
    LAB
    0.07
    _into
    0.07
    ing
    0.07
    mÄĽ
    0.06
    .Expressions
    0.06
     Into
    0.06
    into
    0.06
    mmc
    0.06
    Activations Density 0.016%

    No Known Activations