© 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. 129239
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numerical values

    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
     èĩ
    -0.08
    Ø´Ùģ
    -0.06
    oulos
    -0.06
     gate
    -0.05
     dim
    -0.05
    orf
    -0.05
    annt
    -0.05
    wind
    -0.05
    oler
    -0.05
    945
    -0.05
    POSITIVE LOGITS
    asl
    0.08
    eza
    0.07
    onis
    0.07
    uter
    0.07
    åĪ¶åº¦
    0.07
    abo
    0.07
    artin
    0.07
    svp
    0.06
    .rs
    0.06
     Champ
    0.06
    Activations Density 0.000%

    No Known Activations