© 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. 16769
    Prev
    Next
    INDEX
    Explanations

    geographical locations and addresses

    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
    holm
    -0.06
    anagan
    -0.06
    iju
    -0.06
    ستاÙĨ
    -0.06
    استاÙĨ
    -0.06
     ><?
    -0.06
    سÙĩ
    -0.06
     Ocak
    -0.06
    ÙĦÙĩ
    -0.06
    ville
    -0.06
    POSITIVE LOGITS
     thi
    0.07
    igure
    0.07
    ivals
    0.06
     awakeFromNib
    0.06
    esium
    0.06
    Ìģ
    0.06
    ideo
    0.06
    PMC
    0.06
    emy
    0.06
    eters
    0.06
    Activations Density 0.013%

    No Known Activations