© 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. 119149
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to countability

    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
    ácil
    -0.08
    iron
    -0.07
    RIES
    -0.07
    oller
    -0.07
    icit
    -0.06
    iro
    -0.06
    ries
    -0.06
    rieve
    -0.06
    ocations
    -0.06
    stav
    -0.06
    POSITIVE LOGITS
     Swinger
    0.06
    ãĥªãĥ³
    0.06
    аÑĢам
    0.06
    struct
    0.06
     Victorian
    0.06
    atable
    0.06
    xdc
    0.06
    ä»ģ
    0.06
    Ñĸдно
    0.06
    .blob
    0.06
    Activations Density 0.209%

    No Known Activations