© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95552
    Prev
    Next
    INDEX
    Explanations

    code-related references and configurations

    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
    .MixedReality
    -0.07
     benign
    -0.06
    _softmax
    -0.06
    eniable
    -0.06
    aphore
    -0.06
    owitz
    -0.06
    èo
    -0.06
    iating
    -0.06
     Terr
    -0.06
    sts
    -0.05
    POSITIVE LOGITS
    ilim
    0.07
    obo
    0.07
     kone
    0.06
    atz
    0.06
    igo
    0.06
    erre
    0.06
     Dek
    0.06
    fare
    0.06
     processData
    0.06
    udden
    0.06
    Activations Density 0.000%

    No Known Activations