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. 21-LLAMASCOPE-RES-32K
    6. 9936
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership or relationships in a personal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zdy
    -0.17
    angkan
    -0.16
    zw
    -0.16
    ạnh
    -0.15
    rani
    -0.15
    ùi
    -0.15
    ContentLoaded
    -0.14
    plusplus
    -0.14
    .googleapis
    -0.14
    .Atomic
    -0.14
    POSITIVE LOGITS
     radar
    0.21
     possession
    0.21
     arsenal
    0.21
     midst
    0.20
     consciousness
    0.19
     lap
    0.19
     life
    0.18
     lex
    0.17
     orbit
    0.17
     vocabulary
    0.17
    Activations Density 0.100%

    No Known Activations