© 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. 26-LLAMASCOPE-RES-32K
    11. 10015
    Prev
    Next
    INDEX
    Explanations

    references to residency and employment status related to locations or jurisdictions

    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
    olik
    -0.17
    otos
    -0.17
    escal
    -0.15
    eka
    -0.15
    edback
    -0.15
    tas
    -0.15
    ÏĨÏħ
    -0.15
    Ïĩε
    -0.14
    elman
    -0.14
    maj
    -0.14
    POSITIVE LOGITS
     residence
    0.33
     resident
    0.30
     Residence
    0.28
     residency
    0.26
     habit
    0.26
     permanent
    0.25
     Resident
    0.25
     habitual
    0.24
     permanently
    0.24
     reside
    0.24
    Activations Density 0.025%

    No Known Activations