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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117976
    Prev
    Next
    INDEX
    Explanations

    nouns related to locations and places

    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
    示
    -0.07
    ASM
    -0.07
    attr
    -0.07
    gie
    -0.07
    s
    -0.07
    scape
    -0.07
    atur
    -0.06
    logical
    -0.06
    shell
    -0.06
     blink
    -0.06
    POSITIVE LOGITS
    shire
    0.10
     Heights
    0.08
    ian
    0.08
    ville
    0.08
    urst
    0.08
    vale
    0.07
    lán
    0.07
     Vale
    0.07
    ussen
    0.07
    ia
    0.07
    Activations Density 0.092%

    No Known Activations