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. 4-LLAMASCOPE-RES-32K
    6. 30942
    Prev
    Next
    INDEX
    Explanations

    terms and references related to geographic locations, particularly places starting with 'G'

    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
    uce
    -0.18
     guise
    -0.16
    _g
    -0.15
    Current
    -0.15
    εν
    -0.14
    exion
    -0.14
    loys
    -0.14
     gentleman
    -0.14
    ym
    -0.14
    cg
    -0.14
    POSITIVE LOGITS
    osate
    0.18
    reich
    0.16
    SSIP
    0.16
     phép
    0.16
    žel
    0.16
    zel
    0.15
    atemala
    0.15
    äºĪ
    0.15
    )frame
    0.14
    ospels
    0.14
    Activations Density 0.989%

    No Known Activations