© 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. 78598
    Prev
    Next
    INDEX
    Explanations

    expressions of admiration or fondness for people or 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
    ucas
    -0.06
    oi
    -0.06
     pit
    -0.06
     abandon
    -0.06
    kus
    -0.06
     Pit
    -0.06
    czy
    -0.06
    anka
    -0.06
     ri
    -0.06
    ensch
    -0.06
    POSITIVE LOGITS
    ENTA
    0.07
     admir
    0.07
    /met
    0.07
    pte
    0.07
     Dispatch
    0.07
    mag
    0.07
    ognito
    0.07
    ÅĻez
    0.07
    jur
    0.06
    _MAGIC
    0.06
    Activations Density 0.031%

    No Known Activations