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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 61063
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'a' or 'i' as single characters

    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
    finity
    -0.07
    LING
    -0.07
    å£
    -0.07
    ibus
    -0.06
    dob
    -0.06
    ract
    -0.06
    ury
    -0.06
    qv
    -0.06
    het
    -0.06
    antan
    -0.06
    POSITIVE LOGITS
    ãĤ¤ãĤ¯
    0.07
    äº
    0.07
    TA
    0.06
    Pk
    0.06
    .EventType
    0.06
    ewire
    0.06
    adece
    0.06
     Ont
    0.06
    .mixin
    0.06
    è¯Ŀ
    0.06
    Activations Density 0.058%

    No Known Activations