© 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. 75223
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or speculation

    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
    rens
    -0.07
    abase
    -0.07
    976
    -0.07
    imon
    -0.07
    AXB
    -0.06
    ä¼ı
    -0.06
    ErrMsg
    -0.06
    iferay
    -0.06
     predomin
    -0.06
    ooky
    -0.06
    POSITIVE LOGITS
     more
    0.07
    Ïĥη
    0.06
    sembles
    0.06
     MORE
    0.06
     sort
    0.06
    sembl
    0.06
    ois
    0.06
    way
    0.06
     kind
    0.06
    anging
    0.06
    Activations Density 0.005%

    No Known Activations