© 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. 10092
    Prev
    Next
    INDEX
    Explanations

    terms and references related to laws and regulations concerning disabilities and public education

    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
    ninger
    -0.14
    æĭ©
    -0.14
    eworld
    -0.13
    íħĶ
    -0.13
    changer
    -0.13
    Ù쨩
    -0.13
    Editors
    -0.13
    //{{
    -0.13
    Mgr
    -0.13
    opher
    -0.13
    POSITIVE LOGITS
     Act
    0.83
     act
    0.71
    Act
    0.63
    _act
    0.55
     Acts
    0.54
    act
    0.51
     ACT
    0.51
    _Act
    0.48
    .act
    0.47
     acts
    0.46
    Activations Density 0.051%

    No Known Activations