© 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. 27-LLAMASCOPE-RES-32K
    11. 12686
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Nin" and its variations, particularly in a context relating to ninjas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edis
    -0.16
    adla
    -0.16
    омеÑĢ
    -0.16
    umhur
    -0.15
    ecycle
    -0.15
    оваÑĢ
    -0.15
    erif
    -0.15
     lạ
    -0.14
    stime
    -0.14
    bsub
    -0.14
    POSITIVE LOGITS
    jas
    0.26
    ETY
    0.25
    ety
    0.22
    ny
    0.22
    eties
    0.21
    jab
    0.20
    ject
    0.20
    jac
    0.19
    veh
    0.18
    jaw
    0.18
    Activations Density 0.008%

    No Known Activations