© 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. 3745
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational missions and goals

    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
     Arena
    -0.07
    lech
    -0.06
    stick
    -0.06
    deaux
    -0.06
    dit
    -0.06
    forth
    -0.06
    dar
    -0.05
    quier
    -0.05
    _ENC
    -0.05
    burger
    -0.05
    POSITIVE LOGITS
    /go
    0.08
    alez
    0.08
     readline
    0.07
    reamble
    0.07
    éĢļãĤĬ
    0.07
    UCCEEDED
    0.07
    iface
    0.07
    imary
    0.07
     rencont
    0.07
    ionario
    0.07
    Activations Density 0.011%

    No Known Activations