© 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. 76893
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel experiences and local culture

    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
    *)((
    -0.07
     íķ´ìĻ¸
    -0.06
    omor
    -0.06
    /front
    -0.06
    olley
    -0.06
    urat
    -0.06
    ستاÙĨ
    -0.06
    Africa
    -0.06
    æµ·å¤ĸ
    -0.06
    Ģ
    -0.06
    POSITIVE LOGITS
     native
    0.22
     locals
    0.20
     natives
    0.18
    native
    0.17
     local
    0.17
    -native
    0.17
     indigenous
    0.15
     Native
    0.15
    locals
    0.15
    _native
    0.14
    Activations Density 0.094%

    No Known Activations