© 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. 57708
    Prev
    Next
    INDEX
    Explanations

    concepts related to necessity and obligation

    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
    isable
    -0.07
    amon
    -0.07
    zac
    -0.06
    things
    -0.06
    ish
    -0.06
    etting
    -0.06
     relent
    -0.06
    orna
    -0.06
     McInt
    -0.06
     Lind
    -0.05
    POSITIVE LOGITS
    sah
    0.07
    éłĪ
    0.07
    erator
    0.07
    edException
    0.07
    éľĢ
    0.07
    edo
    0.07
    ERO
    0.07
    otr
    0.07
     occasion
    0.07
    itated
    0.07
    Activations Density 0.003%

    No Known Activations