© 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. 4153
    Prev
    Next
    INDEX
    Explanations

    names and brand references related to specific entities or organizations

    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
    ahir
    -0.08
    adro
    -0.08
    idor
    -0.07
    ÑĥÑĩа
    -0.07
    ixel
    -0.07
    obil
    -0.07
    uitka
    -0.07
    loy
    -0.07
    ÙİØŃ
    -0.07
    roat
    -0.07
    POSITIVE LOGITS
     twitter
    0.09
     Twitter
    0.09
     tweets
    0.09
     Tweet
    0.07
    official
    0.07
     tweet
    0.07
     Tweets
    0.07
     twe
    0.07
     Follow
    0.07
     tweeted
    0.07
    Activations Density 0.016%

    No Known Activations