© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 14-LLAMASCOPE-RES-32K
    6. 9895
    Prev
    Next
    INDEX
    Explanations

    references to innocence and innocent victims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illisecond
    -0.21
    رÙĤ
    -0.16
    alama
    -0.16
    CJK
    -0.16
    _sink
    -0.15
    tlement
    -0.15
    าà¸ĩ
    -0.15
    tle
    -0.15
    aq
    -0.15
    .TestTools
    -0.14
    POSITIVE LOGITS
     innocent
    0.22
     innocence
    0.21
     innoc
    0.19
     bystand
    0.19
     Innoc
    0.19
    -looking
    0.17
    ubs
    0.17
     pure
    0.16
    /un
    0.16
    elyn
    0.16
    Activations Density 0.026%

    No Known Activations