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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40112
    Prev
    Next
    INDEX
    Explanations

    references to freedom and free market concepts

    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
    ngen
    -0.07
    Ñİдж
    -0.07
    oka
    -0.07
    nej
    -0.06
    keley
    -0.06
    ENUM
    -0.06
    éĿ
    -0.06
    lexer
    -0.06
    icopter
    -0.06
    chy
    -0.06
    POSITIVE LOGITS
    (er
    0.08
     freely
    0.07
     markets
    0.07
    ness
    0.07
     society
    0.07
    bie
    0.06
     movement
    0.06
    ãĥ³ãĥĶ
    0.06
     speech
    0.06
    fulness
    0.06
    Activations Density 0.010%

    No Known Activations