© 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. 119018
    Prev
    Next
    INDEX
    Explanations

    terms related to guarantees and warranties

    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
    _ISR
    -0.07
    bote
    -0.07
    ilo
    -0.07
    oley
    -0.06
    eden
    -0.06
    -cigaret
    -0.06
    ÑĥлÑĮ
    -0.06
    erview
    -0.06
     kata
    -0.06
    mayan
    -0.06
    POSITIVE LOGITS
    ulp
    0.08
    quat
    0.07
    oreach
    0.07
    utz
    0.06
    hashtags
    0.06
    '].$
    0.06
    zers
    0.06
    chez
    0.06
    orgot
    0.06
    loub
    0.06
    Activations Density 0.005%

    No Known Activations