© 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. 26-LLAMASCOPE-RES-32K
    6. 28786
    Prev
    Next
    INDEX
    Explanations

    references to pop music and its various sub-genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     population
    -0.17
    population
    -0.17
    olini
    -0.16
    entication
    -0.16
    ors
    -0.16
     Population
    -0.16
    Population
    -0.16
    hots
    -0.16
     populations
    -0.16
    _population
    -0.15
    POSITIVE LOGITS
    py
    0.21
    star
    0.20
    üler
    0.20
    ulist
    0.19
    pii
    0.19
    nika
    0.19
    ularity
    0.19
    nable
    0.18
    ulaire
    0.18
    -cultural
    0.18
    Activations Density 0.007%

    No Known Activations