© 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. 94737
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with" indicating relationships or permissions

    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
    annon
    -0.08
    zá
    -0.06
    ge
    -0.06
    aries
    -0.06
    ony
    -0.06
    ral
    -0.06
    tha
    -0.06
    ValidationError
    -0.06
     trouble
    -0.06
    at
    -0.06
    POSITIVE LOGITS
     permission
    0.11
    permission
    0.09
     PERMISSION
    0.09
     Permission
    0.08
    FRING
    0.08
    _permission
    0.08
    .scal
    0.08
    .ManyToMany
    0.08
     permissions
    0.07
    LPARAM
    0.07
    Activations Density 0.003%

    No Known Activations