© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    references to lip care and application processes

    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
    cascade
    -0.06
     Pod
    -0.06
     hải
    -0.06
     Wort
    -0.06
     наÑģÑĤ
    -0.06
    cestor
    -0.06
    aire
    -0.06
    éĶ¦
    -0.06
     golden
    -0.05
     bending
    -0.05
    POSITIVE LOGITS
     Lips
    0.10
     lips
    0.10
     lip
    0.09
    åĶĩ
    0.08
     lipstick
    0.08
    ervals
    0.07
     Pink
    0.07
    oker
    0.07
     Lip
    0.07
    .cmd
    0.07
    Activations Density 0.001%

    No Known Activations