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. 17897
    Prev
    Next
    INDEX
    Explanations

    species of animals, particularly those associated with nature and wildlife

    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
    iminal
    -0.15
    isible
    -0.15
    íķ©
    -0.14
    orative
    -0.14
    eut
    -0.14
    ÙĪØ²Ùĩ
    -0.14
    uries
    -0.14
    enty
    -0.14
    ContextHolder
    -0.14
    edReader
    -0.14
    POSITIVE LOGITS
    skin
    0.25
    -shaped
    0.23
    bane
    0.23
    /go
    0.23
    kin
    0.21
    /cat
    0.21
    -human
    0.21
     population
    0.20
     species
    0.19
     carc
    0.19
    Activations Density 0.189%

    No Known Activations