© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16915
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reaffirm" and its variations, indicating a focus on the theme of reasserting or confirming principles or claims

    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
     McCarthy
    -0.20
     wil
    -0.17
    otch
    -0.16
     Mehr
    -0.16
     sectional
    -0.16
    smarty
    -0.15
    окол
    -0.15
    734
    -0.14
    prefix
    -0.14
     Hyp
    -0.14
    POSITIVE LOGITS
    ois
    0.18
     Barg
    0.17
    á»ģ
    0.15
    ÏĢοι
    0.15
    _diag
    0.15
     éŁ
    0.15
     пÑĢид
    0.15
     bohat
    0.14
    chos
    0.14
    lop
    0.14
    Activations Density 0.028%

    No Known Activations