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. 23-LLAMASCOPE-RES-32K
    6. 770
    Prev
    Next
    INDEX
    Explanations

    names of people and their related activities or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fucked
    -0.27
    fuck
    -0.25
     fuck
    -0.23
     FUCK
    -0.22
    Fuck
    -0.21
     fucking
    -0.21
     fucks
    -0.21
     Fuck
    -0.20
     religion
    -0.19
     religions
    -0.19
    POSITIVE LOGITS
     ministry
    0.27
     convict
    0.22
     relational
    0.21
     Christ
    0.21
     ministries
    0.20
    Script
    0.20
     Christians
    0.20
     God
    0.19
     parach
    0.18
     NT
    0.18
    Activations Density 1.556%

    No Known Activations