© 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. 5-LLAMASCOPE-RES-131K
    11. 126019
    Prev
    Next
    INDEX
    Explanations

    references to materials and environmental considerations in product descriptions

    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
    lea
    -0.07
    rets
    -0.07
    ÑĸÑĪ
    -0.07
    iev
    -0.07
     Nah
    -0.06
    ola
    -0.06
    ers
    -0.06
    士
    -0.06
     Dos
    -0.06
    xor
    -0.06
    POSITIVE LOGITS
     å±
    0.07
    è²
    0.06
     suyu
    0.06
    jang
    0.06
    CompatActivity
    0.06
    Ñıем
    0.06
    amina
    0.06
    svc
    0.06
     Burl
    0.06
    ãĤ¯ãĥŃ
    0.06
    Activations Density 0.000%

    No Known Activations