© 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. 17-LLAMASCOPE-RES-131K
    6. 76408
    Prev
    Next
    INDEX
    Explanations

    references to political or social activists and their statements

    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
    erna
    -0.07
    á»ĥ
    -0.07
    lich
    -0.07
    ilig
    -0.07
    nyder
    -0.06
    abeth
    -0.06
    expects
    -0.06
    edom
    -0.06
     overposting
    -0.06
    ÐļÐĺ
    -0.06
    POSITIVE LOGITS
     co
    0.07
    çļĦä¸Ģ
    0.06
    pub
    0.06
     spectrum
    0.06
     spray
    0.06
     help
    0.06
    ilere
    0.05
     Spectrum
    0.05
    _REFERENCE
    0.05
    çѾ
    0.05
    Activations Density 0.010%

    No Known Activations