© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60801
    Prev
    Next
    INDEX
    Explanations

    intense negative feelings or hatred expressed toward various subjects 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
    ÑĤÑĮ
    -0.07
    elles
    -0.07
    483
    -0.06
    scribe
    -0.06
    227
    -0.06
    erie
    -0.06
    ystick
    -0.06
    osaic
    -0.06
    337
    -0.06
    inions
    -0.06
    POSITIVE LOGITS
    /conf
    0.07
    furt
    0.07
    woord
    0.07
    acen
    0.07
    enga
    0.07
    aren
    0.07
    LOAT
    0.06
    fully
    0.06
    bilder
    0.06
    AZY
    0.06
    Activations Density 0.010%

    No Known Activations