© 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. 12-LLAMASCOPE-RES-32K
    11. 28938
    Prev
    Next
    INDEX
    Explanations

    varying levels of emotional responses and punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    925
    -0.16
    íħ
    -0.15
    nel
    -0.14
    719
    -0.14
    730
    -0.14
    елÑı
    -0.14
    601
    -0.14
    ux
    -0.14
     Levin
    -0.14
    anny
    -0.14
    POSITIVE LOGITS
    illac
    0.15
    ebi
    0.15
    arma
    0.14
    orado
    0.14
    dings
    0.14
    verture
    0.14
    BASH
    0.13
    ritch
    0.13
    echn
    0.13
    hardt
    0.13
    Activations Density 0.046%

    No Known Activations