© 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. 29-LLAMASCOPE-RES-32K
    11. 3408
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that express hypothetical situations or possibilities

    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
     indispens
    -0.18
    (always
    -0.15
    nga
    -0.15
     underrated
    -0.15
     annoy
    -0.14
    AsyncResult
    -0.14
    urf
    -0.14
     addictive
    -0.14
    ernet
    -0.14
    CLAIM
    -0.14
    POSITIVE LOGITS
     rem
    0.35
     nice
    0.27
    nice
    0.23
     would
    0.21
     wise
    0.21
     Nice
    0.20
     rash
    0.20
    Nice
    0.20
     Rem
    0.19
    Would
    0.19
    Activations Density 0.075%

    No Known Activations