© 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. 38807
    Prev
    Next
    INDEX
    Explanations

    terms related to positioning or directionality in contexts of incidents or events

    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
    tent
    -0.07
    egative
    -0.06
    à¹Ħà¸Ľ
    -0.06
    ikat
    -0.06
    avic
    -0.06
    ##_
    -0.06
    ismu
    -0.06
    assis
    -0.06
     evasion
    -0.06
    chio
    -0.06
    POSITIVE LOGITS
    ç³»
    0.07
     safety
    0.07
     Safety
    0.06
    سÙĪب
    0.06
    iji
    0.06
     Controls
    0.06
    iams
    0.06
    /stdc
    0.06
    Ìģ
    0.06
    ijo
    0.06
    Activations Density 0.000%

    No Known Activations