© 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. 15-LLAMASCOPE-RES-131K
    11. 87762
    Prev
    Next
    INDEX
    Explanations

    numerical data related to phone number combinations and area codes

    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
    á»ĩ
    -0.08
    ãĥ¼ãĤ¯
    -0.06
    _nsec
    -0.06
    ÃŃnh
    -0.06
    isk
    -0.06
    _AES
    -0.06
     renamed
    -0.06
    cplusplus
    -0.06
    drs
    -0.06
    ói
    -0.06
    POSITIVE LOGITS
    reau
    0.07
    akeup
    0.07
     misd
    0.07
     Prest
    0.06
     land
    0.06
     IDD
    0.06
    Lookup
    0.06
     Land
    0.06
     trunk
    0.06
     Brooke
    0.06
    Activations Density 0.010%

    No Known Activations