© 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. 30-LLAMASCOPE-RES-32K
    6. 22899
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical social structures or roles

    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
     Medina
    -0.18
     Morr
    -0.18
    adesh
    -0.17
     Mirage
    -0.17
     Miranda
    -0.16
    shint
    -0.16
    midd
    -0.16
     Millet
    -0.15
     Monument
    -0.15
     militants
    -0.14
    POSITIVE LOGITS
     master
    1.09
     Master
    1.03
    master
    0.97
    Master
    0.96
    -master
    0.94
    _master
    0.89
     MASTER
    0.88
     masters
    0.85
    .master
    0.85
    MASTER
    0.80
    Activations Density 0.059%

    No Known Activations