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. 24-LLAMASCOPE-RES-32K
    6. 21195
    Prev
    Next
    INDEX
    Explanations

    expressions of extreme flavor or taste in food and beverages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rix
    -0.17
    ani
    -0.15
    rial
    -0.15
    apor
    -0.15
     regards
    -0.14
    leton
    -0.14
    unt
    -0.14
    uder
    -0.14
    RL
    -0.14
    atu
    -0.14
    POSITIVE LOGITS
    hung
    0.22
     boot
    0.17
     quote
    0.17
    eless
    0.17
    å¤Ħ
    0.16
    jours
    0.15
    ehr
    0.15
    tes
    0.15
    ether
    0.15
     date
    0.15
    Activations Density 0.194%

    No Known Activations