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. 23-LLAMASCOPE-RES-32K
    6. 11847
    Prev
    Next
    INDEX
    Explanations

    content related to free services and offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ³
    -0.17
    ouz
    -0.15
    :animated
    -0.14
    ãĥķãĥ¬
    -0.14
    ÙĨØ´
    -0.13
     lạc
    -0.13
    UiThread
    -0.13
     extrad
    -0.13
    ERCHANT
    -0.13
    zell
    -0.12
    POSITIVE LOGITS
     free
    1.31
    free
    1.11
     FREE
    1.09
    FREE
    0.97
     Free
    0.96
    åħįè´¹
    0.96
     gratis
    0.95
    -free
    0.93
    Free
    0.92
    _free
    0.90
    Activations Density 0.527%

    No Known Activations