© 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. 62478
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and details about them

    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
     domestic
    -0.08
     Domestic
    -0.08
    avage
    -0.06
    457
    -0.06
     Consort
    -0.06
     Commod
    -0.06
     Tape
    -0.06
    avar
    -0.06
     domest
    -0.06
     tape
    -0.05
    POSITIVE LOGITS
    ophone
    0.08
     sinc
    0.07
    ARB
    0.07
     pie
    0.07
    vla
    0.07
     Baum
    0.07
    sterol
    0.07
    ÏĦÏī
    0.06
     vÄĽt
    0.06
    REW
    0.06
    Activations Density 0.030%

    No Known Activations