© 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. 41372
    Prev
    Next
    INDEX
    Explanations

    references to specific organizational structures and categories

    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
     something
    -0.07
     my
    -0.07
     mah
    -0.06
     indeed
    -0.06
     complementary
    -0.06
     rather
    -0.06
     rival
    -0.06
     a
    -0.06
     etc
    -0.06
     perhaps
    -0.06
    POSITIVE LOGITS
    gnore
    0.08
    subclass
    0.08
     ONLY
    0.08
    except
    0.07
    .onView
    0.07
    CEPT
    0.07
    okud
    0.07
     domic
    0.07
    lacak
    0.07
    oxic
    0.07
    Activations Density 0.006%

    No Known Activations