© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 11257
    Prev
    Next
    INDEX
    Explanations

    critiques of common storytelling tropes and clichés in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avad
    -0.16
    (defvar
    -0.16
    /downloads
    -0.15
    owler
    -0.15
    iets
    -0.14
    à¥Ģमत
    -0.14
    ाण
    -0.13
    raki
    -0.13
    icensing
    -0.13
    lesh
    -0.13
    POSITIVE LOGITS
     familiar
    0.44
     trop
    0.38
     tired
    0.35
     clich
    0.31
     predictable
    0.31
     trope
    0.31
     classic
    0.30
     tried
    0.30
     familiarity
    0.28
     Fam
    0.28
    Activations Density 0.217%

    No Known Activations