© 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. 119575
    Prev
    Next
    INDEX
    Explanations

    expressions of anxiety and suicidal thoughts

    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
     Serif
    -0.07
    415
    -0.07
    aux
    -0.07
    Ey
    -0.07
    annon
    -0.06
    SSIP
    -0.06
     char
    -0.06
    ighet
    -0.06
    çĬ¯
    -0.06
    itech
    -0.06
    POSITIVE LOGITS
     depression
    0.08
    uko
    0.07
     dep
    0.07
     depressed
    0.07
     завиÑģим
    0.06
     hiding
    0.06
    ialis
    0.06
    -hide
    0.06
     Dep
    0.06
     day
    0.06
    Activations Density 0.049%

    No Known Activations