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. 17376
    Prev
    Next
    INDEX
    Explanations

    the frequent use of the word "that" in various contexts

    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
    ity
    -0.16
    ushman
    -0.15
    amp
    -0.15
    Ùĩ
    -0.14
    iid
    -0.14
    ignet
    -0.14
    aille
    -0.14
    s
    -0.14
    umno
    -0.13
       
    -0.13
    POSITIVE LOGITS
    /th
    0.23
    ched
    0.19
    zelf
    0.18
    ãĥ³ãĤ¬
    0.17
    chers
    0.17
    -sex
    0.16
    curity
    0.16
    annah
    0.16
    yonel
    0.16
    obe
    0.15
    Activations Density 0.130%

    No Known Activations