© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126638
    Prev
    Next
    INDEX
    Explanations

    locations or names related to places

    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
    arus
    -0.08
    aris
    -0.08
    aran
    -0.08
    ing
    -0.07
    úsqueda
    -0.07
    er
    -0.06
    ings
    -0.06
    iminal
    -0.06
    aday
    -0.06
    _NATIVE
    -0.06
    POSITIVE LOGITS
    adium
    0.07
     Valk
    0.07
    gon
    0.07
    naire
    0.07
    esthesia
    0.07
    Skeleton
    0.07
    onical
    0.06
    richt
    0.06
    ally
    0.06
    ven
    0.06
    Activations Density 0.001%

    No Known Activations