© 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. 126424
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "moving" in various contexts

    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
    blr
    -0.07
    ovol
    -0.07
    =Value
    -0.07
    undry
    -0.07
    ings
    -0.07
    κÏģι
    -0.06
    842
    -0.06
    ertools
    -0.06
    ůj
    -0.06
    atra
    -0.06
    POSITIVE LOGITS
    ame
    0.09
    AME
    0.09
    /sl
    0.07
    ly
    0.07
    ames
    0.07
    redient
    0.06
     moving
    0.06
    /static
    0.06
    reek
    0.06
    ostat
    0.06
    Activations Density 0.012%

    No Known Activations