© 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. 118349
    Prev
    Next
    INDEX
    Explanations

    references to the American Civil Liberties Union (ACLU) and its leadership or affiliates

    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
    åı
    -0.08
    elman
    -0.07
    Rotation
    -0.06
    iquid
    -0.06
    ely
    -0.06
    orb
    -0.06
    udio
    -0.06
     dissolve
    -0.06
     geil
    -0.06
    lem
    -0.06
    POSITIVE LOGITS
    uggage
    0.07
    atatype
    0.07
    .org
    0.06
    ustos
    0.06
     Boyle
    0.06
    ahoma
    0.06
    oscope
    0.06
    jez
    0.06
    issors
    0.06
     Theodore
    0.06
    Activations Density 0.019%

    No Known Activations