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. 18241
    Prev
    Next
    INDEX
    Explanations

    expressions of affection and positive traits about individuals

    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
     yourselves
    -0.15
     sensations
    -0.15
     anonym
    -0.13
     Inspiration
    -0.13
    iso
    -0.13
     Sentry
    -0.13
    знаÑĩ
    -0.13
    ç´ł
    -0.13
    adt
    -0.13
    ijing
    -0.13
    POSITIVE LOGITS
     dry
    0.26
     personality
    0.26
     manner
    0.25
     presence
    0.25
     infectious
    0.24
     wit
    0.22
     warmth
    0.21
     magnet
    0.21
     intelligence
    0.21
     sense
    0.20
    Activations Density 0.249%

    No Known Activations