© 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. 40857
    Prev
    Next
    INDEX
    Explanations

    references to cookie policies and user consent on websites

    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
    unden
    -0.06
    igg
    -0.06
     Dia
    -0.06
    ords
    -0.06
    å¡
    -0.06
    stdin
    -0.06
     din
    -0.06
    urge
    -0.05
     fan
    -0.05
    akan
    -0.05
    POSITIVE LOGITS
    çĵ
    0.07
    ÑĤаж
    0.06
    TabControl
    0.06
    gnore
    0.06
    à¸ģà¸ķ
    0.06
    QueryBuilder
    0.06
    POR
    0.06
    memberof
    0.06
    lla
    0.06
    Stride
    0.06
    Activations Density 0.002%

    No Known Activations