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. 31-LLAMASCOPE-RES-32K
    6. 2093
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'G' in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    filer
    -0.17
    #ac
    -0.16
    580
    -0.16
    DataContract
    -0.14
    abilities
    -0.14
    uncio
    -0.14
    xico
    -0.14
    erdem
    -0.14
    GenerationStrategy
    -0.14
    apolis
    -0.14
    POSITIVE LOGITS
    ives
    0.33
    onna
    0.32
    ive
    0.31
    otta
    0.31
    ave
    0.31
    IVE
    0.29
    iving
    0.28
    otten
    0.28
    oes
    0.26
    reet
    0.26
    Activations Density 0.027%

    No Known Activations