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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7763
    Prev
    Next
    INDEX
    Explanations

    references to album sales and commercial success metrics

    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
    ÏĦιÏĥ
    -0.16
     Bai
    -0.16
    arkin
    -0.16
     overd
    -0.15
    rani
    -0.15
     Mansion
    -0.14
    aland
    -0.14
    oui
    -0.14
    amin
    -0.14
    _NOP
    -0.13
    POSITIVE LOGITS
    isure
    0.16
    BorderColor
    0.15
    ylum
    0.15
    ardım
    0.15
    /cop
    0.15
    μμε
    0.15
    gary
    0.14
    licer
    0.14
    _HAND
    0.14
    emetery
    0.14
    Activations Density 0.028%

    No Known Activations