© 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. 73154
    Prev
    Next
    INDEX
    Explanations

    terms related to returning or backward movement in context

    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
    ãĥ³ãĥij
    -0.07
     Buccane
    -0.07
    zial
    -0.06
    ruž
    -0.06
    /***/
    -0.06
    ÑĪев
    -0.06
    utely
    -0.06
    /use
    -0.06
    roll
    -0.06
    izione
    -0.06
    POSITIVE LOGITS
    ertoire
    0.06
    ambda
    0.06
    éĢĢ
    0.06
    /back
    0.06
    pective
    0.06
    Permanent
    0.06
    anda
    0.06
    ahr
    0.05
    aclass
    0.05
    dden
    0.05
    Activations Density 0.003%

    No Known Activations