© 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. 2052
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of a "clip" or "clipping" in various contexts

    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
     clay
    -0.17
    keeping
    -0.17
    ApiClient
    -0.16
    ooks
    -0.15
     clinical
    -0.15
    woke
    -0.15
    ÅĻes
    -0.14
    lingen
    -0.14
    _claim
    -0.14
    climate
    -0.14
    POSITIVE LOGITS
    ä¼¼
    0.20
    wise
    0.19
    avel
    0.17
    opath
    0.17
    ey
    0.17
    borne
    0.17
    ifton
    0.17
    arity
    0.17
    ifornia
    0.16
    voy
    0.16
    Activations Density 0.091%

    No Known Activations