© 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. 118860
    Prev
    Next
    INDEX
    Explanations

    expressions related to geographical regions and locations

    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
    ettel
    -0.08
    ober
    -0.07
    hsi
    -0.07
    oger
    -0.07
    oldem
    -0.07
    zo
    -0.07
    illac
    -0.07
    colo
    -0.07
    azzi
    -0.06
    ODY
    -0.06
    POSITIVE LOGITS
    /world
    0.07
     Duchess
    0.07
    cue
    0.06
    oses
    0.06
    keh
    0.06
    -wide
    0.06
    /state
    0.06
    naires
    0.06
    $MESS
    0.06
    storybook
    0.06
    Activations Density 0.001%

    No Known Activations