Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43412
    Prev
    Next
    INDEX
    Explanations

    references to crises and the impact of societal issues

    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
    .;↵
    -0.06
    .;
    -0.06
    2
    -0.05
    4
    -0.05
    oki
    -0.05
    ingo
    -0.05
    1
    -0.05
    ]='\
    -0.05
    elia
    -0.05
    3
    -0.05
    POSITIVE LOGITS
     says
    0.21
     say
    0.19
    says
    0.17
     Says
    0.17
     warns
    0.17
    say
    0.14
     claims
    0.14
     argues
    0.14
     according
    0.14
     warn
    0.13
    Activations Density 0.035%

    No Known Activations