© 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. 24-LLAMASCOPE-RES-32K
    11. 20846
    Prev
    Next
    INDEX
    Explanations

    concepts related to safety and security

    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
     Safety
    -0.45
     safety
    -0.45
     safely
    -0.44
    Safety
    -0.42
     safer
    -0.39
     safest
    -0.36
     saf
    -0.35
    safe
    -0.35
     Safe
    -0.34
     safe
    -0.34
    POSITIVE LOGITS
     sound
    0.22
     Sound
    0.21
    Sound
    0.20
     Secure
    0.18
    Sec
    0.17
    sound
    0.17
     secure
    0.17
     sec
    0.17
    erville
    0.17
     SOUND
    0.17
    Activations Density 0.028%

    No Known Activations