© 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. 15-LLAMASCOPE-RES-131K
    11. 61719
    Prev
    Next
    INDEX
    Explanations

    scientific references and citations in academic papers

    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
    /MIT
    -0.07
    iclass
    -0.07
    ibase
    -0.07
    ÙĪاÙĨ
    -0.07
    .addField
    -0.06
     nÄĥ
    -0.06
    -host
    -0.06
    652
    -0.06
    host
    -0.06
    cry
    -0.06
    POSITIVE LOGITS
    apur
    0.07
    βολ
    0.07
    ĶåĽŀ
    0.06
     Horm
    0.06
    addtogroup
    0.06
    opp
    0.06
    APH
    0.06
    defgroup
    0.06
    emez
    0.06
    .identifier
    0.05
    Activations Density 0.001%

    No Known Activations