© 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. 76728
    Prev
    Next
    INDEX
    Explanations

    references to ideological affiliations and conflicts

    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
     Rum
    -0.08
    ICC
    -0.07
    olley
    -0.07
     cyk
    -0.07
    .foreach
    -0.07
    Skin
    -0.07
    Looper
    -0.07
    Owner
    -0.07
     owner
    -0.07
     rumor
    -0.07
    POSITIVE LOGITS
     who
    0.07
    -lite
    0.06
     themselves
    0.06
     marginal
    0.06
    iaux
    0.06
     often
    0.06
    们
    0.06
    *
    0.06
     soph
    0.06
     groups
    0.05
    Activations Density 0.067%

    No Known Activations