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. 7-LLAMASCOPE-RES-32K
    6. 13852
    Prev
    Next
    INDEX
    Explanations

    words related to clothing and apparel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ader
    -0.15
    ial
    -0.14
    åł
    -0.14
    amar
    -0.13
    šlo
    -0.13
     Lun
    -0.13
    ional
    -0.13
    xed
    -0.13
    bler
    -0.13
    blings
    -0.13
    POSITIVE LOGITS
    reh
    0.17
    arent
    0.17
    оба
    0.16
    pcf
    0.16
    ober
    0.15
    âĶ£
    0.15
    lice
    0.15
    опÑĢи
    0.14
     NSLocalizedString
    0.14
    -ie
    0.14
    Activations Density 0.030%

    No Known Activations