Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 22158
    Prev
    Next
    INDEX
    Explanations

    concepts related to progress and liberal ideology in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubat
    -0.17
    εÏģο
    -0.15
    avax
    -0.15
     Turing
    -0.15
    empo
    -0.14
    itler
    -0.14
    ecd
    -0.14
    aku
    -0.14
    PointerType
    -0.14
    rez
    -0.14
    POSITIVE LOGITS
    Lock
    0.32
     Hob
    0.30
     Locke
    0.29
     Lock
    0.28
     Bent
    0.28
     Raw
    0.24
     LOCK
    0.23
    .Lock
    0.23
    Raw
    0.22
     Burke
    0.22
    Activations Density 0.047%

    No Known Activations