© 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. 57641
    Prev
    Next
    INDEX
    Explanations

    future-oriented verbs indicating actions or events

    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
    ´Ī
    -0.07
    ãĥ³ãĤ¹
    -0.07
    nze
    -0.07
    odies
    -0.07
    adol
    -0.06
    Invoker
    -0.06
    amics
    -0.06
    usal
    -0.06
    ámara
    -0.06
    itura
    -0.06
    POSITIVE LOGITS
     fashion
    0.08
     Fashion
    0.07
    URE
    0.07
    andon
    0.06
    _maps
    0.06
     als
    0.06
    arrow
    0.06
    ิà¸ĩ
    0.06
     Moder
    0.06
    esh
    0.06
    Activations Density 0.015%

    No Known Activations