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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-LLAMASCOPE-RES-32K
    6. 2345
    Prev
    Next
    INDEX
    Explanations

    the continuous form of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooth
    -0.15
    entin
    -0.14
    EdgeInsets
    -0.14
    å·»
    -0.14
    éĻº
    -0.14
    crast
    -0.13
    edicine
    -0.13
    him
    -0.13
    mlin
    -0.13
    Scr
    -0.13
    POSITIVE LOGITS
    ades
    0.14
    ĤŃ
    0.14
    DTD
    0.14
    á»Ĺng
    0.14
    semblies
    0.13
    gage
    0.13
    ëħĢ
    0.13
    ometric
    0.13
    otypes
    0.13
    pod
    0.13
    Activations Density 0.054%

    No Known Activations