© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 18530
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and exclamation points

    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
    _TA
    -0.14
     davran
    -0.13
    ÑĢÑĥÑĪ
    -0.12
     minul
    -0.12
    output
    -0.12
    виÑĤ
    -0.12
    â̦)↵↵
    -0.12
    module
    -0.12
    SupportedContent
    -0.12
    data
    -0.12
    POSITIVE LOGITS
    heck
    0.27
    "
    0.23
    yeah
    0.22
    hey
    0.20
    ya
    0.20
    oh
    0.20
    ugh
    0.20
    okay
    0.20
    (
    0.20
    UGH
    0.19
    Activations Density 0.182%

    No Known Activations