© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129434
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to mathematical problems and tests of congruence

    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
    l
    -0.07
     Lens
    -0.06
     Bless
    -0.06
    echan
    -0.06
    Compat
    -0.06
     unsur
    -0.05
    v
    -0.05
    xing
    -0.05
    .Exists
    -0.05
    /global
    -0.05
    POSITIVE LOGITS
    ábado
    0.08
    oggler
    0.08
     Byl
    0.08
    ONSE
    0.08
    /*č↵
    0.08
    Ø·ÙĨ
    0.08
    ÑģÑĤоÑĢ
    0.07
    _('
    0.07
    uxe
    0.07
    ลาย
    0.07
    Activations Density 0.001%

    No Known Activations