© 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. 15-LLAMASCOPE-RES-131K
    11. 27287
    Prev
    Next
    INDEX
    Explanations

    instances of negation or absence in communication

    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
    IVAL
    -0.07
    TOT
    -0.07
    ë³µ
    -0.07
    drv
    -0.06
    GetInstance
    -0.06
    toy
    -0.06
    MOVED
    -0.06
    recated
    -0.06
    akov
    -0.06
    WND
    -0.06
    POSITIVE LOGITS
     physically
    0.09
     physical
    0.08
     formal
    0.08
     direct
    0.08
     directly
    0.07
     formally
    0.07
     explicitly
    0.07
    yer
    0.07
     conventional
    0.07
     explicit
    0.07
    Activations Density 0.075%

    No Known Activations