© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 16570
    Prev
    Next
    INDEX
    Explanations

    overall assessments and evaluations of quality or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overall
    -0.25
    overall
    -0.25
     Overall
    -0.23
    Overall
    -0.21
     altogether
    -0.20
    Æ°Æ¡ng
    -0.18
    apult
    -0.15
    iji
    -0.14
    embro
    -0.14
    iel
    -0.14
    POSITIVE LOGITS
     impression
    0.26
     picture
    0.24
    igator
    0.22
    ìłģìĿ¸
    0.20
     impressions
    0.20
    ìłģìľ¼ë¡ľ
    0.19
    mente
    0.19
     package
    0.19
    -purpose
    0.19
     Picture
    0.18
    Activations Density 0.033%

    No Known Activations