© 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. 126191
    Prev
    Next
    INDEX
    Explanations

    key phrases related to crime and investigations

    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
    owards
    -0.10
    orgen
    -0.07
     Towards
    -0.07
    rowse
    -0.06
     ìĥģ
    -0.06
     incid
    -0.06
    èĥ½å¤Ł
    -0.06
    pta
    -0.06
    igm
    -0.06
    idor
    -0.06
    POSITIVE LOGITS
    ÙĩÙĨ
    0.07
     '
    0.07
    arat
    0.07
     "'
    0.06
    684
    0.06
     Andersen
    0.06
    probe
    0.06
    -'
    0.06
    ziel
    0.06
    .Cmd
    0.06
    Activations Density 0.133%

    No Known Activations