© 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. 29288
    Prev
    Next
    INDEX
    Explanations

    elements related to nostalgia and historical legacy

    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
    -Length
    -0.07
    masked
    -0.07
    ctrine
    -0.07
    ISR
    -0.07
    gni
    -0.06
    Ỽ
    -0.06
    Minute
    -0.06
    ãĥijãĥ³
    -0.06
    acente
    -0.06
    дом
    -0.06
    POSITIVE LOGITS
     past
    0.23
    past
    0.18
     Past
    0.17
    Past
    0.15
    _past
    0.14
    è¿ĩåİ»
    0.14
     previous
    0.13
     old
    0.13
     yesterday
    0.13
     pasado
    0.13
    Activations Density 0.125%

    No Known Activations