© 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. 4-LLAMASCOPE-RES-32K
    11. 14726
    Prev
    Next
    INDEX
    Explanations

    mentions of New Jersey and its associated entities

    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
    424
    -0.17
    obe
    -0.15
    .messaging
    -0.15
    asso
    -0.15
    allet
    -0.15
    Qualified
    -0.14
    esor
    -0.14
    jez
    -0.14
    ctor
    -0.14
     Ngb
    -0.14
    POSITIVE LOGITS
     Devils
    0.16
    lew
    0.15
    embre
    0.15
     Albert
    0.15
    LA
    0.14
    roz
    0.14
    _ht
    0.14
    HM
    0.14
    utenberg
    0.13
     WaitForSeconds
    0.13
    Activations Density 0.011%

    No Known Activations