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. 2-LLAMASCOPE-RES-32K
    6. 5470
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing commitment or dedication to specific goals or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mez
    -0.18
     pry
    -0.14
    nun
    -0.14
    ylon
    -0.14
    dea
    -0.14
    erule
    -0.14
    bole
    -0.14
     odds
    -0.14
    eres
    -0.13
    iamond
    -0.13
    POSITIVE LOGITS
    æĽ¸
    0.19
    anka
    0.15
    书
    0.15
    @student
    0.14
    izza
    0.14
    (Cl
    0.13
     griev
    0.13
     Deniz
    0.13
    eters
    0.13
    DESCRIPTION
    0.13
    Activations Density 0.014%

    No Known Activations