© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61240
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations such as cities, towns, and communities

    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
    .INSTANCE
    -0.08
     ChÃŃnh
    -0.07
    ubi
    -0.07
     puerto
    -0.07
    ardi
    -0.07
    ึà¸ĩ
    -0.07
    óm
    -0.07
    Pu
    -0.07
    agen
    -0.06
    odate
    -0.06
    POSITIVE LOGITS
     surrounding
    0.08
    :;"
    0.07
     Surround
    0.07
    pon
    0.06
    ToProps
    0.06
    orgetown
    0.06
     Burr
    0.06
    icum
    0.06
    landa
    0.06
    845
    0.06
    Activations Density 0.011%

    No Known Activations