© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27009
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations or street names

    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
    zÅij
    -0.07
    ennie
    -0.07
    feito
    -0.07
    zik
    -0.07
    /REC
    -0.07
    aldi
    -0.07
    ÑįÑĤ
    -0.07
    classnames
    -0.06
    ft
    -0.06
    imity
    -0.06
    POSITIVE LOGITS
     street
    0.07
    arket
    0.07
    elik
    0.06
     Street
    0.06
    alley
    0.06
     streets
    0.06
    759
    0.06
     Feld
    0.06
    street
    0.06
    wise
    0.06
    Activations Density 0.001%

    No Known Activations