Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 20620
    Prev
    Next
    INDEX
    Explanations

    expressions of existence and state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lesh
    -0.15
    à¸Ļาม
    -0.14
    ware
    -0.14
    [Index
    -0.14
    LastError
    -0.13
    hint
    -0.13
    ึ
    -0.13
    好ãģį
    -0.13
    oun
    -0.13
    ges
    -0.12
    POSITIVE LOGITS
     below
    0.63
    Below
    0.54
     Below
    0.54
    以ä¸ĭ
    0.54
    below
    0.53
    å¦Ĥä¸ĭ
    0.48
     BELOW
    0.44
     following
    0.42
     ниже
    0.40
     abaixo
    0.40
    Activations Density 0.001%

    No Known Activations