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. 25-LLAMASCOPE-RES-32K
    6. 16652
    Prev
    Next
    INDEX
    Explanations

    the verb "do" 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 @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aint
    -0.15
    hood
    -0.15
    mania
    -0.15
    wards
    -0.15
    ائج
    -0.15
    athan
    -0.15
    udio
    -0.15
    cy
    -0.15
    opoulos
    -0.15
    anta
    -0.15
    POSITIVE LOGITS
    cket
    0.22
     justice
    0.21
    ctest
    0.21
     wrong
    0.20
    ctr
    0.19
     differently
    0.18
    ÅĤÄħ
    0.18
    oming
    0.18
    oooo
    0.17
    ctors
    0.17
    Activations Density 0.056%

    No Known Activations