© 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. 107417
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions involving matrices and algebraic operations

    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
    andan
    -0.06
    rot
    -0.06
    StateChanged
    -0.06
    éri
    -0.06
    Orm
    -0.06
    tam
    -0.06
    寺
    -0.05
    ense
    -0.05
    ombok
    -0.05
    .Template
    -0.05
    POSITIVE LOGITS
    uffix
    0.07
    rees
    0.07
    ţi
    0.07
    ÑĢави
    0.07
    Ø´ÙĨ
    0.07
     PUR
    0.07
    ernal
    0.07
    ť
    0.07
    ÑĢÑĥп
    0.06
    ueue
    0.06
    Activations Density 0.181%

    No Known Activations