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. 43581
    Prev
    Next
    INDEX
    Explanations

    concepts related to memes and the impact of popular culture on individual beliefs

    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
    atı
    -0.07
    ÙĦاÙģ
    -0.07
    .ga
    -0.06
     pestic
    -0.06
    zl
    -0.06
    ensored
    -0.06
    ÑĨÑİ
    -0.06
    asser
    -0.06
    ophil
    -0.06
    spender
    -0.06
    POSITIVE LOGITS
     individuals
    0.09
     Individuals
    0.09
     adequate
    0.08
     suitable
    0.08
     obtained
    0.08
     sufficient
    0.08
     appropriate
    0.07
     proper
    0.07
     ideal
    0.07
     incorrect
    0.07
    Activations Density 0.026%

    No Known Activations