© 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. 18153
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "bear" in different contexts

    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
    yle
    -0.07
    ForMember
    -0.07
    iset
    -0.07
    rt
    -0.07
    irie
    -0.07
    å½Ĵ
    -0.06
    ġ
    -0.06
    zano
    -0.06
    aping
    -0.06
    zac
    -0.06
    POSITIVE LOGITS
     witness
    0.12
     resemblance
    0.09
     Witness
    0.08
     testimony
    0.08
     fruit
    0.08
     responsibility
    0.08
    ibold
    0.07
    fruit
    0.07
     Gry
    0.06
    ers
    0.06
    Activations Density 0.007%

    No Known Activations