© 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. 4997
    Prev
    Next
    INDEX
    Explanations

    technical components related to digital and analog circuitry

    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
    orate
    -0.16
    éĻ¢
    -0.15
    tero
    -0.15
    :UIAlert
    -0.14
    ordin
    -0.14
    IFY
    -0.14
    otte
    -0.13
    -grade
    -0.13
     Formatter
    -0.13
    idget
    -0.13
    POSITIVE LOGITS
    -Based
    0.23
    -based
    0.23
    éĺµ
    0.18
     Manufacturers
    0.17
     placement
    0.17
    iar
    0.17
    330
    0.16
    éĻ£
    0.16
    -equipped
    0.16
     selection
    0.16
    Activations Density 0.024%

    No Known Activations