© 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. 20-LLAMASCOPE-RES-32K
    11. 21196
    Prev
    Next
    INDEX
    Explanations

    instances of threats and intimidation directed towards individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gorit
    -0.17
    itech
    -0.16
    оваÑĢ
    -0.14
    ocker
    -0.14
    emo
    -0.14
    inha
    -0.14
     inflicted
    -0.13
    ocyte
    -0.13
    FAST
    -0.13
    .React
    -0.13
    POSITIVE LOGITS
     threats
    0.33
     intimid
    0.25
     threat
    0.25
     intimidation
    0.25
     targeted
    0.24
     Threat
    0.24
    -threat
    0.23
     safety
    0.23
     harassment
    0.23
     threatened
    0.22
    Activations Density 0.154%

    No Known Activations