© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 126727
    Prev
    Next
    INDEX
    Explanations

    affirmations or positive expressions about people and experiences

    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
    orges
    -0.07
    usercontent
    -0.06
    lol
    -0.06
    oder
    -0.06
    ÅĪ
    -0.06
     att
    -0.06
     ap
    -0.06
    .metro
    -0.06
    ally
    -0.05
    linkplain
    -0.05
    POSITIVE LOGITS
    601
    0.07
     NEGLIGENCE
    0.07
    jedn
    0.07
     CHUNK
    0.07
    .pen
    0.06
    .backends
    0.06
    osti
    0.06
    sst
    0.06
    á»ĵn
    0.06
    ìĪľ
    0.06
    Activations Density 0.001%

    No Known Activations