© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 79167
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to violence or criminal acts

    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
    ="{!!
    -0.07
    aktu
    -0.07
    claimer
    -0.07
     smb
    -0.07
    roadcast
    -0.07
    Tube
    -0.07
    .Expr
    -0.07
    isiyle
    -0.07
    weeney
    -0.07
    ehler
    -0.06
    POSITIVE LOGITS
    andal
    0.06
     Firstly
    0.06
     cazzo
    0.06
     firstly
    0.06
    anzeigen
    0.05
    ano
    0.05
    ?key
    0.05
     alot
    0.05
    ko
    0.05
     Rao
    0.05
    Activations Density 0.000%

    No Known Activations