© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 7-LLAMASCOPE-RES-32K
    6. 12649
    Prev
    Next
    INDEX
    Explanations

    Keywords or phrases related to various services and customer experiences, particularly focused on window replacements and home improvement

    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
    hol
    -0.22
    hand
    -0.21
    hide
    -0.20
    hattan
    -0.19
    har
    -0.17
    etti
    -0.17
    hood
    -0.17
    hit
    -0.17
    Ùĩ
    -0.17
    hard
    -0.17
    POSITIVE LOGITS
    ting
    0.35
    ted
    0.25
    ãģĬãĤĬ
    0.23
    imestep
    0.23
    iffany
    0.22
    aylor
    0.22
    olkien
    0.21
    ters
    0.21
    esseract
    0.21
    itled
    0.21
    Activations Density 2.392%

    No Known Activations