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. 24-LLAMASCOPE-RES-32K
    6. 19177
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize customization and personalization according to individual needs and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alace
    -0.17
    zyst
    -0.15
    illac
    -0.15
    rud
    -0.15
    ehr
    -0.15
    echan
    -0.14
    issant
    -0.14
    rous
    -0.14
    nde
    -0.14
    iez
    -0.14
    POSITIVE LOGITS
     needs
    0.59
     requirements
    0.54
    needs
    0.49
     Needs
    0.47
    requirements
    0.44
     Requirements
    0.42
    Needs
    0.41
    Requirements
    0.38
     preferences
    0.38
     requirement
    0.37
    Activations Density 0.284%

    No Known Activations