Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 87
    Prev
    Next
    INDEX
    Explanations

    references to data manipulation and merging in programming, specifically in Python using pandas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yard
    -0.15
    auen
    -0.14
    umph
    -0.14
     Peg
    -0.13
    dent
    -0.13
    .hxx
    -0.13
    ↵↵
    -0.13
    Digits
    -0.13
     Detroit
    -0.13
     discrimin
    -0.13
    POSITIVE LOGITS
     Pand
    0.45
     df
    0.43
     pandas
    0.40
     DataFrame
    0.39
     pd
    0.38
     DF
    0.38
    df
    0.38
     dataframe
    0.36
    DF
    0.36
    (df
    0.34
    Activations Density 0.047%

    No Known Activations