© 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. 17-LLAMASCOPE-RES-131K
    6. 106093
    Prev
    Next
    INDEX
    Explanations

    geographical or locational terms

    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
    meli
    -0.08
    cmc
    -0.08
    wort
    -0.08
    exampleModal
    -0.08
    ạ
    -0.08
    ÑģÑĤоÑĢ
    -0.08
    iddi
    -0.08
    edom
    -0.08
    ekler
    -0.08
    essler
    -0.07
    POSITIVE LOGITS
    cle
    0.06
     near
    0.05
     New
    0.05
    urse
    0.05
     AD
    0.05
    let
    0.05
    342
    0.05
     Bren
    0.05
    as
    0.05
     left
    0.05
    Activations Density 0.001%

    No Known Activations