© 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. 106800
    Prev
    Next
    INDEX
    Explanations

    names and titles of various constituencies or organizations

    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
     Ukra
    -0.06
    amon
    -0.06
    asher
    -0.06
    วà¸Ķ
    -0.06
    ī
    -0.06
    ankind
    -0.06
    upa
    -0.06
     cresc
    -0.06
     jenter
    -0.06
    uce
    -0.06
    POSITIVE LOGITS
    ension
    0.07
    venge
    0.07
    isphere
    0.06
    nev
    0.06
    MOTE
    0.06
    æķħ
    0.06
    ноÑģÑĤ
    0.06
    enberg
    0.06
    elijk
    0.06
    enstein
    0.06
    Activations Density 0.020%

    No Known Activations