© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 13134
    Prev
    Next
    INDEX
    Explanations

    references to legal representation and guidance in custody modification cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arsers
    -0.15
    ãĥ³ãĥĨãĤ£
    -0.14
    ullah
    -0.14
    Wrapped
    -0.14
     Hanson
    -0.13
    YC
    -0.13
     late
    -0.13
    楽ãģĹ
    -0.13
    =".$_
    -0.13
    rita
    -0.13
    POSITIVE LOGITS
     can
    0.28
     will
    0.27
    ä¼ļ
    0.24
     knows
    0.23
     know
    0.21
    åı¯ä»¥
    0.20
    éĥ½ä¼ļ
    0.20
     offer
    0.19
     helps
    0.19
    æľĥ
    0.19
    Activations Density 0.126%

    No Known Activations