© 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. 29614
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'E' in various contexts and formats

    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
    mi
    -0.09
    j
    -0.08
    lo
    -0.08
    lem
    -0.08
    m
    -0.08
    na
    -0.07
    nce
    -0.07
    оз
    -0.07
    ase
    -0.07
    li
    -0.07
    POSITIVE LOGITS
    hx
    0.09
    ÑĥÑħ
    0.07
    aque
    0.07
    itom
    0.07
    olian
    0.07
    ukan
    0.07
    asier
    0.07
    isd
    0.07
    legg
    0.07
    enton
    0.07
    Activations Density 0.117%

    No Known Activations