© 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. 18-LLAMASCOPE-RES-32K
    6. 28911
    Prev
    Next
    INDEX
    Explanations

    references to the name "Castiel" or related variations that pertain to this character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akin
    -0.16
    unday
    -0.16
    ÑģÑĮ
    -0.16
    iating
    -0.14
    rå
    -0.14
    rist
    -0.14
    uez
    -0.14
    ostat
    -0.14
    naire
    -0.14
    uliar
    -0.14
    POSITIVE LOGITS
    igated
    0.24
    ellan
    0.24
    igation
    0.23
    .Cast
    0.23
    aways
    0.23
     Cast
    0.23
    igate
    0.23
     cast
    0.19
    caster
    0.18
    ings
    0.18
    Activations Density 0.022%

    No Known Activations