© 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. 9-LLAMASCOPE-RES-32K
    11. 16670
    Prev
    Next
    INDEX
    Explanations

    references to deception or inauthenticity in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cigaret
    -0.17
    irie
    -0.15
    lamaz
    -0.15
    rosso
    -0.14
    ounge
    -0.14
    axy
    -0.14
    HX
    -0.14
    okoj
    -0.14
    afx
    -0.14
    ÏĢλ
    -0.14
    POSITIVE LOGITS
     normal
    0.19
    ellung
    0.16
    _EXTENSIONS
    0.15
     Mara
    0.14
    оÑī
    0.14
    è¾ij
    0.14
    NORMAL
    0.13
    ARA
    0.13
    ico
    0.13
     membrane
    0.13
    Activations Density 0.045%

    No Known Activations