© 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. 78150
    Prev
    Next
    INDEX
    Explanations

    instances of the word "currently" and related time-based descriptors indicating ongoing situations

    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
    itler
    -0.07
    ych
    -0.07
    positor
    -0.07
    ivec
    -0.07
    wiki
    -0.06
    ẩm
    -0.06
    adal
    -0.06
    iza
    -0.06
    hani
    -0.06
    iveau
    -0.06
    POSITIVE LOGITS
    arters
    0.06
    !=(
    0.06
     tot
    0.06
     Accepted
    0.05
    (Target
    0.05
     Mam
    0.05
    à¹ĩà¸Ķ
    0.05
     figure
    0.05
    isclosed
    0.05
    utz
    0.05
    Activations Density 0.001%

    No Known Activations