Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4755
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating various states or conditions

    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
    _mD
    -0.08
    好ãģį
    -0.07
    iverz
    -0.07
    rush
    -0.07
    chwitz
    -0.07
    andez
    -0.07
    _mC
    -0.07
    μη
    -0.07
    _inches
    -0.07
    linger
    -0.07
    POSITIVE LOGITS
    angered
    0.07
     talented
    0.07
     liter
    0.06
    phans
    0.06
     tattoo
    0.06
    -haired
    0.06
    -trained
    0.06
    hood
    0.06
    piring
    0.06
    innen
    0.06
    Activations Density 0.101%

    No Known Activations