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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 2860
    Prev
    Next
    INDEX
    Explanations

    names of people and their affiliations or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Christ
    -0.19
     christian
    -0.17
     Christian
    -0.17
     Baptist
    -0.15
    illet
    -0.15
    Christian
    -0.15
     pastor
    -0.15
    ngr
    -0.15
     Pastor
    -0.14
    ación
    -0.14
    POSITIVE LOGITS
     Shapiro
    0.27
     Jewish
    0.26
     Levine
    0.25
    owitz
    0.24
     Feinstein
    0.24
     Epstein
    0.23
     Jews
    0.23
     Rabbi
    0.22
     Rubin
    0.22
     jewish
    0.21
    Activations Density 0.173%

    No Known Activations