Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30-LLAMASCOPE-RES-32K
    6. 19395
    Prev
    Next
    INDEX
    Explanations

    themes related to challenging social norms and barriers

    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
    638
    -0.16
     à¤Ĩत
    -0.15
    ysl
    -0.15
     Nobel
    -0.15
    جÙĨ
    -0.13
    Hands
    -0.13
    ìļķ
    -0.13
    igin
    -0.13
    iÅŁim
    -0.13
     Brennan
    -0.12
    POSITIVE LOGITS
     convention
    0.40
     conventions
    0.36
     conventional
    0.34
     norms
    0.34
     established
    0.32
     accepted
    0.31
     conformity
    0.30
     orth
    0.29
     Convention
    0.28
     expectations
    0.28
    Activations Density 0.241%

    No Known Activations