© 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. 76993
    Prev
    Next
    INDEX
    Explanations

    elements related to academic or research references

    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
    vince
    -0.07
    intree
    -0.07
    094
    -0.07
    linky
    -0.07
     attachment
    -0.06
    >manual
    -0.06
     Shel
    -0.06
    訴
    -0.06
    riteln
    -0.06
    rador
    -0.06
    POSITIVE LOGITS
    inne
    0.07
    eid
    0.06
    âĨ
    0.06
    .atom
    0.06
     twig
    0.06
     DOI
    0.06
     Article
    0.06
     journal
    0.06
    atoria
    0.06
    ihu
    0.06
    Activations Density 0.037%

    No Known Activations