© 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. 60795
    Prev
    Next
    INDEX
    Explanations

    phrases related to mental health and its challenges

    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
    phia
    -0.08
    ocol
    -0.08
     Lyons
    -0.08
    اضر
    -0.08
     rost
    -0.07
     Replies
    -0.07
    ehr
    -0.07
    lys
    -0.07
    lij
    -0.07
    licative
    -0.07
    POSITIVE LOGITS
     said
    0.07
     enh
    0.07
     says
    0.06
     recently
    0.06
     (
    0.06
     feels
    0.06
     character
    0.06
     بÙĪابة
    0.06
     has
    0.06
     felt
    0.05
    Activations Density 0.030%

    No Known Activations