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. 17-LLAMASCOPE-RES-32K
    6. 21611
    Prev
    Next
    INDEX
    Explanations

    discussions around standards and expectations, particularly in educational and behavioral contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inke
    -0.16
    unma
    -0.15
    strup
    -0.15
    arih
    -0.15
    аÑĢи
    -0.15
    dux
    -0.14
    elage
    -0.14
    izza
    -0.14
    ari
    -0.14
    @Module
    -0.14
    POSITIVE LOGITS
     standards
    0.45
     expectations
    0.42
     demanding
    0.37
     Standards
    0.35
     demands
    0.32
     Expect
    0.31
     expectation
    0.31
    Expect
    0.30
    expect
    0.30
    è¦ģæ±Ĥ
    0.30
    Activations Density 0.200%

    No Known Activations