© 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. 29-LLAMASCOPE-RES-32K
    11. 18282
    Prev
    Next
    INDEX
    Explanations

    terms related to validation, policies, and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ','.
    -0.13
    Č
    -0.13
    ãĢģ“
    -0.13
    ,',
    -0.12
    "",↵
    -0.12
     "...
    -0.12
    ;o
    -0.12
     ,.
    -0.12
    ','-
    -0.12
    ,",
    -0.12
    POSITIVE LOGITS
    :
    1.09
    ा:
    0.63
     :
    0.58
    ï¼ļ
    0.57
    à¹Į:
    0.55
    *:
    0.53
    +:
    0.52
    :↵
    0.51
    _:
    0.51
    ?:
    0.50
    Activations Density 2.453%

    No Known Activations