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. 27-LLAMASCOPE-RES-32K
    6. 53
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hm
    -0.14
    gtk
    -0.14
    imestone
    -0.13
    regation
    -0.13
     enjo
    -0.13
    platz
    -0.13
     DataAccess
    -0.13
    arah
    -0.13
    imers
    -0.13
    ãģķãģĽ
    -0.13
    POSITIVE LOGITS
     Whe
    0.22
     Anchor
    0.19
     Coaching
    0.19
     Shoulder
    0.18
     coaching
    0.18
     Coach
    0.18
     Bull
    0.18
     Spread
    0.18
    Anchor
    0.18
     Assembly
    0.17
    Activations Density 0.040%

    No Known Activations