Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106634
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic locations and specific descriptors associated with them

    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
    izon
    -0.07
    ason
    -0.06
    upe
    -0.06
    iri
    -0.06
    acock
    -0.06
    662
    -0.06
    headed
    -0.06
    imei
    -0.06
    окон
    -0.06
    ÑģÑı
    -0.06
    POSITIVE LOGITS
    -style
    0.12
     style
    0.10
     Style
    0.09
    -type
    0.09
    -region
    0.08
    style
    0.08
    å¼ı
    0.08
     type
    0.08
    ian
    0.08
    ese
    0.08
    Activations Density 0.032%

    No Known Activations