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. 31-LLAMASCOPE-RES-32K
    6. 18253
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and phrases indicating personal perspective or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breakdown
    -0.14
    è²Ŀ
    -0.14
     legit
    -0.14
    ίγ
    -0.14
    ipur
    -0.14
     sworn
    -0.13
    imity
    -0.13
    Util
    -0.13
    ihat
    -0.13
    ñas
    -0.13
    POSITIVE LOGITS
     shall
    0.24
     hast
    0.24
     confess
    0.21
     da
    0.20
     note
    0.19
     incl
    0.19
     reproduce
    0.18
     accordingly
    0.18
    pres
    0.17
     presum
    0.17
    Activations Density 0.271%

    No Known Activations