Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5708
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations or streets

    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
    á¾
    -0.07
    ayscale
    -0.06
     porad
    -0.06
    _ALIGNMENT
    -0.06
    echan
    -0.06
     èĹ
    -0.06
    athers
    -0.06
    ÑģÑĤин
    -0.06
    echa
    -0.06
     tj
    -0.06
    POSITIVE LOGITS
     Principal
    0.07
    imet
    0.07
     Suff
    0.07
     General
    0.06
     access
    0.06
    incipal
    0.06
    Principal
    0.06
     Independ
    0.06
    udev
    0.06
    atus
    0.06
    Activations Density 0.006%

    No Known Activations