© 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. 129004
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the intention or action of 'to do' something

    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
     continued
    -0.09
     continuing
    -0.09
    continued
    -0.07
     continue
    -0.07
     continues
    -0.07
    uries
    -0.07
    ffect
    -0.07
    ll
    -0.07
     continuation
    -0.07
    ward
    -0.07
    POSITIVE LOGITS
    abouts
    0.07
    Rotor
    0.07
     поба
    0.07
    ying
    0.06
    ycz
    0.06
    nings
    0.06
    eper
    0.06
    ÏģÏĮÏĤ
    0.06
    INGS
    0.06
    698
    0.06
    Activations Density 0.011%

    No Known Activations