© 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 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. 17-LLAMASCOPE-RES-131K
    11. 57286
    Prev
    Next
    INDEX
    Explanations

    references to reading, watching visual media, and personal experiences related to long-form storytelling, such as memoirs

    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
    agger
    -0.07
    amd
    -0.07
    skirts
    -0.07
    ohana
    -0.06
    AMD
    -0.06
    rolley
    -0.06
    orne
    -0.06
    ÙĪاÙĨ
    -0.06
    efs
    -0.06
    egade
    -0.06
    POSITIVE LOGITS
     anymore
    0.15
     unless
    0.13
     nor
    0.13
    unless
    0.12
     myself
    0.10
     except
    0.10
     Unless
    0.10
    Unless
    0.10
    except
    0.09
     anything
    0.09
    Activations Density 0.036%

    No Known Activations