© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 12-LLAMASCOPE-RES-32K
    11. 18000
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mention" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    баÑĩ
    -0.15
    jmp
    -0.15
    deaux
    -0.15
    ìĸ´ëĤĺ
    -0.14
    анов
    -0.14
    ì¹ĺëĬĶ
    -0.14
     Suche
    -0.14
    Ħĸ
    -0.14
    anova
    -0.14
    icina
    -0.13
    POSITIVE LOGITS
    mention
    0.15
     ³³ ³³ ³³ ³³
    0.15
     Busty
    0.15
    akra
    0.14
     mention
    0.14
    sa
    0.14
     menc
    0.14
     wards
    0.14
     Mention
    0.14
    ables
    0.14
    Activations Density 0.028%

    No Known Activations