© 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. 57095
    Prev
    Next
    INDEX
    Explanations

    expressions of concern or reassurance regarding writing and its process

    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
    imit
    -0.08
    ATUS
    -0.07
    AVIS
    -0.07
    ARAM
    -0.07
    avou
    -0.07
    umpt
    -0.07
    /Gate
    -0.07
    ANTE
    -0.07
    dma
    -0.06
    itu
    -0.06
    POSITIVE LOGITS
     worry
    0.17
     worrying
    0.16
     concern
    0.16
     worries
    0.14
     Concern
    0.14
     concerns
    0.14
     preocup
    0.13
     worried
    0.13
     concerned
    0.12
    Concern
    0.12
    Activations Density 0.036%

    No Known Activations