© 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. 25-LLAMASCOPE-RES-32K
    11. 15625
    Prev
    Next
    INDEX
    Explanations

    contractions and possessive forms in informal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’t
    -0.23
    ’re
    -0.22
    ’n
    -0.21
    ’na
    -0.20
    ’m
    -0.20
     ‘
    -0.20
    ’T
    -0.19
    ’hui
    -0.18
    ’ta
    -0.18
    ’d
    -0.18
    POSITIVE LOGITS
    /'
    0.25
    ÂĢÂĻ
    0.24
    -'
    0.24
    ¦
    0.22
    -"
    0.20
    ':
    0.19
    ()'
    0.18
    âĶIJ
    0.18
    ...'
    0.17
    /"
    0.17
    Activations Density 0.060%

    No Known Activations