© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 2-LLAMASCOPE-RES-32K
    11. 290
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements of rowing machines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterol
    -0.17
    abcdefghijkl
    -0.15
    tam
    -0.15
    quam
    -0.15
    enus
    -0.14
    okane
    -0.14
    ivar
    -0.14
    .Dot
    -0.14
     shape
    -0.14
    .Override
    -0.14
    POSITIVE LOGITS
    273
    0.15
    440
    0.15
     Proud
    0.14
     Clearly
    0.14
     Dra
    0.14
    361
    0.14
    439
    0.14
    441
    0.14
    nis
    0.13
    heels
    0.13
    Activations Density 0.061%

    No Known Activations