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. 11-LLAMASCOPE-RES-32K
    6. 20778
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial matters and ownership questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alu
    -0.14
    xAA
    -0.14
    SSIP
    -0.13
    dech
    -0.13
    acent
    -0.13
    atto
    -0.13
    èĬĿ
    -0.13
     پا
    -0.13
     relational
    -0.13
     Publications
    -0.13
    POSITIVE LOGITS
     rather
    0.17
     chứ
    0.16
    hey
    0.15
     already
    0.15
    dea
    0.14
     adm
    0.14
    ÑĢаб
    0.14
     Lol
    0.14
    .tt
    0.14
     /
    0.14
    Activations Density 0.249%

    No Known Activations