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. 14-LLAMASCOPE-RES-32K
    6. 13249
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "give" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rad
    -0.16
    eful
    -0.16
    aver
    -0.15
    ÑģÑĭлки
    -0.15
     Pazar
    -0.15
    prov
    -0.14
     behalf
    -0.14
    IGHL
    -0.14
    reeze
    -0.13
     ingen
    -0.13
    POSITIVE LOGITS
     rise
    0.24
    äºĪ
    0.18
    892
    0.18
    aways
    0.17
    vous
    0.16
    chter
    0.16
     us
    0.16
    SCO
    0.15
    å®ļçļĦ
    0.15
    away
    0.15
    Activations Density 0.084%

    No Known Activations