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. 30-LLAMASCOPE-RES-32K
    6. 24437
    Prev
    Next
    INDEX
    Explanations

    statistics and data related to education and employment trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -0.34
     vỼi
    -0.31
     dengan
    -0.29
    with
    -0.29
    	with
    -0.28
    ewith
    -0.24
     avec
    -0.24
    swith
    -0.24
    _with
    -0.22
     withString
    -0.22
    POSITIVE LOGITS
     being
    0.38
     having
    0.36
    being
    0.32
     intact
    0.31
     thrown
    0.29
    having
    0.27
     remaining
    0.27
     becoming
    0.27
     included
    0.26
     sendo
    0.26
    Activations Density 0.442%

    No Known Activations