Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4885
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tend" and variations of it, indicating a focus on topics related to tendencies or habits

    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
    omain
    -0.07
    panion
    -0.07
    obel
    -0.07
    umes
    -0.07
    phin
    -0.06
    pone
    -0.06
    odic
    -0.06
    osate
    -0.06
    ampie
    -0.06
    èĻ«
    -0.06
    POSITIVE LOGITS
    ulk
    0.09
    леÑĩ
    0.07
     Harr
    0.07
     Momentum
    0.07
     ADM
    0.06
    TypeInfo
    0.06
     SOS
    0.06
    TypeName
    0.06
     McInt
    0.06
     Opr
    0.06
    Activations Density 0.001%

    No Known Activations