© 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. 12-LLAMASCOPE-RES-32K
    11. 20005
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    engin
    -0.16
    icken
    -0.14
    ilion
    -0.14
    веÑģÑĤи
    -0.14
    Ľå»º
    -0.14
    eln
    -0.14
    ierz
    -0.13
    ÏįÏĦε
    -0.13
    ÌĨ
    -0.13
    лоб
    -0.13
    POSITIVE LOGITS
    dorf
    0.17
     trace
    0.15
    pty
    0.15
    _variant
    0.15
     Trace
    0.14
    trace
    0.14
    ullah
    0.13
    åĿĽ
    0.13
    orm
    0.13
    ilers
    0.13
    Activations Density 0.019%

    No Known Activations