© 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. 56980
    Prev
    Next
    INDEX
    Explanations

    terms related to freedom of speech and legal restrictions on it

    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
    .Bunifu
    -0.08
    strict
    -0.08
    okit
    -0.08
    strup
    -0.08
    amac
    -0.08
    verbatim
    -0.07
     Paginator
    -0.07
    arget
    -0.07
    empl
    -0.07
    istra
    -0.07
    POSITIVE LOGITS
     reasonable
    0.07
    ocrates
    0.06
     others
    0.06
     forfe
    0.06
     society
    0.06
    cho
    0.06
     Cave
    0.06
     cave
    0.05
     Derek
    0.05
     liberty
    0.05
    Activations Density 0.021%

    No Known Activations