© 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. 5-LLAMASCOPE-RES-131K
    11. 125874
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "times" and its variations in relation to frequency or occurrences in a situation

    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
    iesel
    -0.08
    _ser
    -0.08
    ski
    -0.07
    znám
    -0.07
    cht
    -0.07
     Král
    -0.07
    ứt
    -0.07
    ampo
    -0.07
    RequestId
    -0.07
    uki
    -0.07
    POSITIVE LOGITS
    ź
    0.06
     æķ
    0.06
     beyond
    0.06
    (s
    0.06
    raph
    0.06
    lessness
    0.06
    logs
    0.05
     cil
    0.05
     Beyond
    0.05
    ady
    0.05
    Activations Density 0.001%

    No Known Activations