© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4193
    Prev
    Next
    INDEX
    Explanations

    concepts related to free speech and its protection under the law

    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
    oop
    -0.07
    egin
    -0.07
    uyu
    -0.07
    ovah
    -0.07
    rades
    -0.07
    lef
    -0.07
    elder
    -0.06
    ä»ķ
    -0.06
     jig
    -0.06
    rone
    -0.06
    POSITIVE LOGITS
     rights
    0.10
     freedom
    0.10
     FRE
    0.09
     protected
    0.09
     guaranteed
    0.09
    fre
    0.09
     freedoms
    0.08
     protections
    0.08
     protection
    0.08
     Rights
    0.08
    Activations Density 0.010%

    No Known Activations