Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 83014
    Prev
    Next
    INDEX
    Explanations

    references to historical entities or events

    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
    ĵĺ
    -0.07
    idis
    -0.06
    amiliar
    -0.06
     inhal
    -0.06
    poons
    -0.06
     hull
    -0.06
    zie
    -0.06
    à¸ģระ
    -0.06
    ESIS
    -0.06
    hf
    -0.06
    POSITIVE LOGITS
     gene
    0.10
    çε
    0.10
    gene
    0.08
    å§ĵ
    0.07
     Gene
    0.07
     pedigree
    0.07
    Surname
    0.07
    Gene
    0.06
     Raven
    0.06
     pedig
    0.06
    Activations Density 0.001%

    No Known Activations