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. 29-LLAMASCOPE-RES-32K
    6. 4510
    Prev
    Next
    INDEX
    Explanations

    instances of the word "My" and its variations, indicating a focus on possessive expressions or personal ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -0.17
    stin
    -0.17
    heads
    -0.16
    ley
    -0.16
    sb
    -0.15
    urgence
    -0.15
    pike
    -0.15
    ognito
    -0.15
    ste
    -0.15
    same
    -0.15
    POSITIVE LOGITS
    rtle
    0.34
    riad
    0.34
    ths
    0.29
    anmar
    0.28
    opic
    0.27
    opia
    0.27
    embros
    0.25
    self
    0.23
    elin
    0.23
    rrha
    0.23
    Activations Density 0.047%

    No Known Activations