© 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. 30-LLAMASCOPE-RES-32K
    6. 23032
    Prev
    Next
    INDEX
    Explanations

    issues related to programming and code functioning, particularly around error handling and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ignor
    -0.16
    .scalablytyped
    -0.15
    à¸į
    -0.15
    è£ľ
    -0.14
    برÛĮ
    -0.14
    imin
    -0.13
     íĤ
    -0.13
     analogy
    -0.13
    OrNil
    -0.13
    agnostic
    -0.13
    POSITIVE LOGITS
     race
    0.30
     corner
    0.26
    race
    0.26
     subtle
    0.25
     races
    0.25
     edge
    0.23
     bugs
    0.23
    Corner
    0.23
    corner
    0.22
     broken
    0.21
    Activations Density 0.280%

    No Known Activations