© 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. 83112
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles indicating possession or association

    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
    nex
    -0.06
    ighton
    -0.06
    ida
    -0.06
    ison
    -0.06
    lds
    -0.06
    ilder
    -0.06
    amm
    -0.06
    ooke
    -0.06
    itten
    -0.06
    Ñ
    -0.06
    POSITIVE LOGITS
     whom
    0.07
    BOOST
    0.07
    LOCKS
    0.07
     turno
    0.07
    locks
    0.07
    rippling
    0.07
    odon
    0.06
    許
    0.06
    viso
    0.06
    ORMAT
    0.06
    Activations Density 0.023%

    No Known Activations