© 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. 17-LLAMASCOPE-RES-131K
    11. 56521
    Prev
    Next
    INDEX
    Explanations

    references to algorithms and programming concepts in a technical context

    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
    ahkan
    -0.07
    -addons
    -0.07
    ioc
    -0.07
    าà¸ĩ
    -0.06
    اغ
    -0.06
    verity
    -0.06
     Krank
    -0.06
    Ïħν
    -0.06
    ılıç
    -0.06
     Getter
    -0.06
    POSITIVE LOGITS
     algorithm
    0.10
     algorithms
    0.09
    Algorithm
    0.08
    algorithm
    0.08
    _algorithm
    0.08
     IMPLEMENT
    0.08
     algo
    0.08
     implementations
    0.08
    Implementation
    0.07
     Algorithm
    0.07
    Activations Density 0.010%

    No Known Activations