© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 15830
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related phrases indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彦
    -0.15
    IntPtr
    -0.14
    å®Ļ
    -0.14
    ernity
    -0.14
    ÑĥÑĢÑĥ
    -0.13
    <&
    -0.13
    lio
    -0.13
    apos
    -0.13
    622
    -0.13
    ãĥ¼ãĥĭ
    -0.13
    POSITIVE LOGITS
     way
    1.35
     Way
    0.98
    way
    0.97
    -way
    0.95
     WAY
    0.93
    Way
    0.85
    .way
    0.84
    _way
    0.82
    WAY
    0.80
    eway
    0.70
    Activations Density 0.075%

    No Known Activations