© 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. 24-LLAMASCOPE-RES-32K
    6. 17767
    Prev
    Next
    INDEX
    Explanations

    expressions related to balance in life and the importance of making choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    алÑİ
    -0.16
    foy
    -0.16
    _mE
    -0.14
    енÑģ
    -0.14
    rink
    -0.14
    tabpanel
    -0.13
    SCII
    -0.13
    radient
    -0.13
    -ÑĤо
    -0.13
    ัà¸Ļม
    -0.13
    POSITIVE LOGITS
     equally
    0.73
     as
    0.69
     igual
    0.37
     stejnÄĽ
    0.36
     equal
    0.36
    	as
    0.35
     как
    0.29
     równ
    0.28
     als
    0.27
     Equal
    0.27
    Activations Density 0.391%

    No Known Activations