© 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. 5168
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to physical actions and the concept of stepping or taking action

    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
    -lfs
    -0.16
    $MESS
    -0.15
    839
    -0.15
    InBackground
    -0.15
    MAS
    -0.14
    ige
    -0.14
    mor
    -0.14
    naments
    -0.14
    .leading
    -0.14
    ranÃŃ
    -0.14
    POSITIVE LOGITS
    ardy
    0.17
    undy
    0.16
    chte
    0.14
    Ñĩе
    0.14
    stock
    0.13
     labour
    0.13
    arus
    0.13
    arta
    0.13
    _INCREMENT
    0.13
    GAN
    0.13
    Activations Density 0.969%

    No Known Activations