© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3849
    Prev
    Next
    INDEX
    Explanations

    instances of the word "handle" and its variations indicating actions related to management or control

    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
    ا
    -0.09
    teenth
    -0.09
    nas
    -0.08
    sb
    -0.08
    çĦ¶
    -0.08
    _UNUSED
    -0.08
    mary
    -0.08
    ALLY
    -0.08
    iê
    -0.07
    okane
    -0.07
    POSITIVE LOGITS
    bars
    0.13
    led
    0.09
    bar
    0.08
    ocrine
    0.07
    ledo
    0.07
    _uploaded
    0.07
    rail
    0.07
    ables
    0.07
    ably
    0.07
    ogue
    0.07
    Activations Density 0.019%

    No Known Activations