© 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. 23-LLAMASCOPE-RES-32K
    11. 28472
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and safeguarding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    еÑģи
    -0.16
    chia
    -0.15
    ansion
    -0.14
    ases
    -0.14
    ceptar
    -0.14
    ÅĻÃŃd
    -0.14
    aison
    -0.14
    eldorf
    -0.14
    quier
    -0.14
    _ctor
    -0.14
    POSITIVE LOGITS
    ETY
    0.26
    eguard
    0.23
    dio
    0.18
    yre
    0.17
    alta
    0.16
    ety
    0.15
     saf
    0.15
    IFEST
    0.15
    AreaView
    0.15
    anko
    0.15
    Activations Density 0.010%

    No Known Activations