© 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. 20-LLAMASCOPE-RES-32K
    11. 11571
    Prev
    Next
    INDEX
    Explanations

    references to promises, commitments, and the act of breaking such pledges in a political or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بط
    -0.16
    eldorf
    -0.16
    ãĤ¶ãĥ¼
    -0.16
    erif
    -0.15
    quo
    -0.15
    ModelIndex
    -0.14
    leared
    -0.14
    disposing
    -0.14
    ozÃŃ
    -0.14
    ouz
    -0.14
    POSITIVE LOGITS
     promise
    0.85
     promises
    0.79
     Promise
    0.70
    promise
    0.65
     promised
    0.63
     commitments
    0.61
     pledge
    0.60
    Promise
    0.60
     commitment
    0.59
     pledges
    0.56
    Activations Density 0.288%

    No Known Activations