© 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. 30-LLAMASCOPE-RES-32K
    11. 16841
    Prev
    Next
    INDEX
    Explanations

    references to the physical manipulation and arrangement of objects or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    εÏĦ
    -0.14
    款
    -0.14
    rve
    -0.13
    feit
    -0.13
    าà¸Ī
    -0.13
    ussen
    -0.13
    pedo
    -0.13
    ãĢģãģĿãģĨ
    -0.13
    JT
    -0.13
    ινÏĮ
    -0.13
    POSITIVE LOGITS
     each
    0.28
     one
    0.28
    top
    0.22
     itself
    0.22
     opposite
    0.20
    each
    0.20
     top
    0.19
     strategic
    0.19
     where
    0.19
     either
    0.19
    Activations Density 0.381%

    No Known Activations