© 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. 18335
    Prev
    Next
    INDEX
    Explanations

    patterns related to document formatting and structure indicators

    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
    ÙĩÙħ
    -0.22
    ÙĢ
    -0.19
    efs
    -0.18
    âĢĮترÛĮÙĨ
    -0.17
    pher
    -0.17
    ee
    -0.17
    ÙĬÙĩ
    -0.16
    ÙĬÙĨ
    -0.16
    ea
    -0.16
    erce
    -0.15
    POSITIVE LOGITS
    iction
    0.28
    extr
    0.24
    roid
    0.24
    istant
    0.23
    igital
    0.21
    rift
    0.21
    nesday
    0.21
    ges
    0.21
    rome
    0.21
    har
    0.21
    Activations Density 0.461%

    No Known Activations