© 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. 125946
    Prev
    Next
    INDEX
    Explanations

    instances of the word "el"

    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
    ivism
    -0.08
    .scalablytyped
    -0.07
    evity
    -0.07
    lian
    -0.07
    EMPLARY
    -0.07
    ysa
    -0.07
    سÙĥ
    -0.07
    abil
    -0.07
    aire
    -0.07
    umberland
    -0.07
    POSITIVE LOGITS
    ucid
    0.07
    idon
    0.07
    leanor
    0.07
    ritch
    0.07
    bv
    0.07
    lements
    0.06
     ect
    0.06
    iot
    0.06
    lico
    0.06
    bis
    0.06
    Activations Density 0.022%

    No Known Activations