© 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. 24-LLAMASCOPE-RES-32K
    11. 6675
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions surrounding safety and the responsibilities associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    анÑĤи
    -0.17
    203
    -0.15
    绩
    -0.14
    CCI
    -0.13
     éĺ
    -0.13
    thenReturn
    -0.13
    _TP
    -0.13
    GenericType
    -0.13
    ableViewController
    -0.12
    Įĵ
    -0.12
    POSITIVE LOGITS
     safety
    1.23
     Safety
    1.04
    Safety
    0.98
    å®īåħ¨
    0.88
     safe
    0.85
    afety
    0.82
     safer
    0.79
    safe
    0.72
     Safe
    0.72
     unsafe
    0.71
    Activations Density 0.427%

    No Known Activations