© 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. 84479
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Eugene."

    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
    ardi
    -0.07
    _MODULE
    -0.06
    ires
    -0.06
    POSITE
    -0.06
    .liferay
    -0.06
    jamin
    -0.06
    eor
    -0.06
    oken
    -0.06
     dequeueReusableCellWithIdentifier
    -0.06
    aron
    -0.06
    POSITIVE LOGITS
    dorf
    0.07
    wald
    0.07
    ois
    0.06
    ska
    0.06
    olars
    0.06
    shi
    0.06
    amt
    0.06
    454
    0.06
    ãĥ¡ãĥ³ãĥĪ
    0.06
    allow
    0.06
    Activations Density 0.002%

    No Known Activations