© 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. 31-LLAMASCOPE-RES-32K
    11. 5771
    Prev
    Next
    INDEX
    Explanations

    monetary figures and legal references in the context of court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñĵ
    -0.15
     Kostenlos
    -0.14
    èŃ
    -0.13
    utenant
    -0.13
    bsp
    -0.13
    _VF
    -0.12
    å½Ĵ
    -0.12
     qed
    -0.12
    itta
    -0.12
     ekip
    -0.12
    POSITIVE LOGITS
     slip
    0.32
     cert
    0.31
     reh
    0.30
     certif
    0.27
     Slip
    0.26
     certs
    0.25
     aff
    0.25
     supra
    0.24
     ¶
    0.24
     rev
    0.24
    Activations Density 0.074%

    No Known Activations