© 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. 31-LLAMASCOPE-RES-32K
    11. 17994
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.29
    HeaderCode
    -0.29
     fetisch
    -0.25
     RuntimeObject
    -0.25
     ëĦ¤ìĿ´íĬ¸
    -0.25
    isContained
    -0.24
    UsageId
    -0.24
    (æľ¨
    -0.24
    NewProp
    -0.23
    Intialized
    -0.23
    POSITIVE LOGITS
    10
    0.49
    2
    0.48
    1
    0.45
    12
    0.44
    3
    0.44
    0
    0.43
    20
    0.43
    18
    0.43
    11
    0.42
    16
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.