© 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. 14245
    Prev
    Next
    INDEX
    Explanations

    references to community, individualism, and social interactions amidst challenges

    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
     Distrib
    -0.14
     lax
    -0.14
     Shortcut
    -0.14
    лам
    -0.13
    ãĤ¹ãĥ¬
    -0.13
     footh
    -0.13
    лÑĮ
    -0.13
    atter
    -0.13
    unct
    -0.13
    æķ·
    -0.13
    POSITIVE LOGITS
     isolation
    0.70
     isolated
    0.66
     isolate
    0.63
     isol
    0.63
    isol
    0.62
     secluded
    0.40
    éļĶ
    0.39
    åѤ
    0.39
    olated
    0.36
    (isolate
    0.35
    Activations Density 0.452%

    No Known Activations