Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 6-LLAMASCOPE-RES-32K
    6. 21377
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns related to personal experiences or belongings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mne
    -0.15
    ymology
    -0.15
    ories
    -0.15
    nable
    -0.15
    olate
    -0.14
    agens
    -0.14
    rug
    -0.14
    ajan
    -0.14
     Mitt
    -0.14
    OnError
    -0.14
    POSITIVE LOGITS
    anmar
    0.21
    rtle
    0.19
    SELF
    0.18
    embros
    0.18
    askell
    0.18
    opia
    0.16
    åĢij
    0.16
    adow
    0.15
    edom
    0.15
    opic
    0.15
    Activations Density 0.125%

    No Known Activations