© 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. 4-LLAMASCOPE-RES-32K
    6. 14718
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "a" or "an" indicating singularity or special moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edn
    -0.17
    jah
    -0.16
    CEED
    -0.16
    ibel
    -0.14
     dro
    -0.14
     druž
    -0.14
    nt
    -0.14
    crest
    -0.14
     جÙĦÙĪ
    -0.14
    506
    -0.13
    POSITIVE LOGITS
    ilda
    0.16
    andid
    0.16
    onda
    0.14
    Overrides
    0.14
     Candid
    0.14
    anda
    0.13
    "http
    0.13
    pus
    0.13
    rrha
    0.13
    ÑģÑĤан
    0.13
    Activations Density 0.345%

    No Known Activations