Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 26-LLAMASCOPE-RES-32K
    6. 27892
    Prev
    Next
    INDEX
    Explanations

    instances of significant injuries or accidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sadd
    -0.16
    longleftrightarrow
    -0.15
     tam
    -0.15
    hil
    -0.14
    vak
    -0.14
     stri
    -0.14
    .Meta
    -0.14
    fsp
    -0.14
    tam
    -0.14
    _STATS
    -0.14
    POSITIVE LOGITS
     Melbourne
    0.23
     Sebastian
    0.20
     Cocoa
    0.18
     Hutchinson
    0.18
     Indian
    0.18
     Treasure
    0.18
    tit
    0.18
    Indian
    0.17
     mel
    0.17
     indian
    0.17
    Activations Density 0.027%

    No Known Activations