© 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. 5-LLAMASCOPE-RES-131K
    11. 126381
    Prev
    Next
    INDEX
    Explanations

    references to skyscrapers

    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
     Patch
    -0.07
     patch
    -0.06
    iming
    -0.06
    roke
    -0.06
     tiên
    -0.06
    utt
    -0.06
    abelle
    -0.06
    uing
    -0.06
    Patch
    -0.06
    veau
    -0.05
    POSITIVE LOGITS
    attern
    0.08
    .AppendFormat
    0.08
    ither
    0.07
    lian
    0.07
    innacle
    0.07
     ******************************************************************************/↵↵
    0.07
    коз
    0.06
    dro
    0.06
    /cop
    0.06
    administration
    0.06
    Activations Density 0.002%

    No Known Activations