Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 28306
    Prev
    Next
    INDEX
    Explanations

    code structures and programming terminology relevant to data handling and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ://%
    -0.18
    ège
    -0.14
    icensed
    -0.14
    enuity
    -0.14
    elo
    -0.14
    legg
    -0.13
    $MESS
    -0.13
    hiba
    -0.13
    .asm
    -0.13
    alim
    -0.13
    POSITIVE LOGITS
     tro
    0.15
     wor
    0.13
    're
    0.13
    etak
    0.13
    OV
    0.13
     Tro
    0.12
    iral
    0.12
    åł¡
    0.12
     bra
    0.12
     pla
    0.12
    Activations Density 0.121%

    No Known Activations