© 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. 95801
    Prev
    Next
    INDEX
    Explanations

    references to murder and related themes

    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
    rick
    -0.07
    ÑģÑĭлки
    -0.07
    lage
    -0.07
    imate
    -0.06
    loha
    -0.06
    oha
    -0.06
    906
    -0.06
    790
    -0.06
    ANC
    -0.06
    alo
    -0.06
    POSITIVE LOGITS
    abilia
    0.09
    ously
    0.09
    ous
    0.08
    joy
    0.08
    -su
    0.08
     Prevention
    0.07
    IFS
    0.07
    hythm
    0.07
     spree
    0.07
    _skb
    0.07
    Activations Density 0.010%

    No Known Activations