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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 595
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to structural integrity and organizational roles

    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
     sometimes
    -0.08
     often
    -0.07
     '
    -0.07
     isn
    -0.07
     shouldn
    -0.06
    oppers
    -0.06
     pop
    -0.06
     may
    -0.06
    eras
    -0.06
     as
    -0.06
    POSITIVE LOGITS
     Äijá»ģu
    0.10
    except
    0.09
    Except
    0.08
     except
    0.08
     Except
    0.08
    ayed
    0.07
    uju
    0.07
    ordinate
    0.07
    koli
    0.07
    leÅŁik
    0.07
    Activations Density 0.056%

    No Known Activations