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. 5-LLAMASCOPE-RES-131K
    6. 126368
    Prev
    Next
    INDEX
    Explanations

    mention of specific locations, particularly cities

    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
    pedia
    -0.07
    åİļ
    -0.07
    ãĥ©ãĤ¹
    -0.06
    ÑģÑĸм
    -0.06
    illo
    -0.06
    hangi
    -0.06
    chner
    -0.06
    vÃŃ
    -0.06
    iciel
    -0.06
    uner
    -0.06
    POSITIVE LOGITS
    quia
    0.07
    usters
    0.07
    lichen
    0.07
    844
    0.07
    xz
    0.06
    dit
    0.06
    scar
    0.06
    aro
    0.06
    urnished
    0.06
    rea
    0.06
    Activations Density 0.001%

    No Known Activations