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. 20-LLAMASCOPE-RES-32K
    6. 28637
    Prev
    Next
    INDEX
    Explanations

    references to the word "Rabbi" and related variations

    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
    nze
    -0.17
    lege
    -0.15
    orks
    -0.15
    _mE
    -0.15
    atör
    -0.14
    sx
    -0.14
    ãĤ¤ãĤ¯
    -0.14
    оÑģÑĤÑĥп
    -0.14
    olia
    -0.14
    umm
    -0.14
    POSITIVE LOGITS
     Rab
    0.20
     rab
    0.19
    cad
    0.18
    idity
    0.18
    rab
    0.16
     Uno
    0.15
    uild
    0.15
    isco
    0.15
    ble
    0.15
    ilitation
    0.14
    Activations Density 0.006%

    No Known Activations