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. 21-LLAMASCOPE-RES-32K
    6. 9624
    Prev
    Next
    INDEX
    Explanations

    instances of existence and conceptualization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¼åIJĪ
    -0.15
    }elseif
    -0.14
    aterno
    -0.14
    ryo
    -0.14
     завиÑģим
    -0.14
    lop
    -0.14
    AYOUT
    -0.14
    eselect
    -0.13
    ÃŃn
    -0.13
    ature
    -0.13
    POSITIVE LOGITS
     existence
    1.15
     exist
    1.13
     exists
    1.12
     Exist
    1.03
     existed
    0.98
    åŃĺåľ¨
    0.92
    exists
    0.91
    existence
    0.91
     Exists
    0.91
    Exist
    0.89
    Activations Density 0.412%

    No Known Activations