© 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. 5-LLAMASCOPE-RES-32K
    11. 18226
    Prev
    Next
    INDEX
    Explanations

    mentions of car brands, particularly luxury brands like Mercedes and Adidas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resa
    -0.16
    _handling
    -0.15
    egal
    -0.14
    eb
    -0.14
    RESH
    -0.14
    owied
    -0.14
    robat
    -0.13
    оÑĩка
    -0.13
    aks
    -0.13
    eg
    -0.13
    POSITIVE LOGITS
    -Benz
    0.18
     Bieber
    0.16
    inde
    0.15
    hausen
    0.15
    parer
    0.15
    γη
    0.15
    roller
    0.14
    warts
    0.14
    Ñģий
    0.14
    -dir
    0.13
    Activations Density 0.001%

    No Known Activations