© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92850
    Prev
    Next
    INDEX
    Explanations

    phrases related to negotiation and conditions

    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
    ì§ĢëıĦ
    -0.07
    ENC
    -0.07
    _VC
    -0.07
     ear
    -0.06
    ewhat
    -0.06
     StringWriter
    -0.06
    ENS
    -0.06
    zcze
    -0.06
    INY
    -0.06
    NC
    -0.06
    POSITIVE LOGITS
     nor
    0.12
    except
    0.11
     except
    0.10
     Except
    0.09
    Except
    0.09
     anymore
    0.09
    nor
    0.09
     unless
    0.08
    _except
    0.08
    unless
    0.07
    Activations Density 0.023%

    No Known Activations