© 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. 25-LLAMASCOPE-RES-32K
    11. 17129
    Prev
    Next
    INDEX
    Explanations

    words associated with deprecation or historical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    สม
    -0.17
    ãĥ¼ãĥĩ
    -0.16
    ayout
    -0.15
    DMIN
    -0.15
    аÑĢаÑĤ
    -0.15
     RequestMethod
    -0.14
    iye
    -0.14
    enville
    -0.14
    reo
    -0.14
    æŀĿ
    -0.14
    POSITIVE LOGITS
     fault
    0.19
     attribute
    0.19
     blame
    0.18
     Credit
    0.18
     credit
    0.17
     attributed
    0.17
    attribute
    0.17
     blamed
    0.16
     Fault
    0.16
    andon
    0.15
    Activations Density 0.015%

    No Known Activations