© 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. 93510
    Prev
    Next
    INDEX
    Explanations

    references to literary works and their impacts

    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
    oyo
    -0.07
    obo
    -0.06
    alu
    -0.06
    zer
    -0.06
    å
    -0.06
    chang
    -0.06
    quist
    -0.06
    oles
    -0.06
    обов
    -0.06
     moż
    -0.06
    POSITIVE LOGITS
    196
    0.09
    195
    0.08
    tees
    0.07
    ÑģÑĤÑİ
    0.06
     Lever
    0.06
    197
    0.06
    mine
    0.06
    ikip
    0.06
    umbn
    0.06
    å¤Ł
    0.06
    Activations Density 0.010%

    No Known Activations