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. 30-LLAMASCOPE-RES-32K
    6. 16941
    Prev
    Next
    INDEX
    Explanations

    phrases related to separation and barriers in relationships or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ«ãģĭ
    -0.13
    WidthSpace
    -0.12
    ------+------+
    -0.12
    Ñĸнки
    -0.12
    ĸìĹIJ
    -0.12
    à¥Ģश
    -0.11
    icont
    -0.11
    ãĤĮãģ©
    -0.11
    voor
    -0.11
    idges
    -0.11
    POSITIVE LOGITS
     from
    1.32
    from
    1.09
     FROM
    0.97
    	from
    0.91
     From
    0.89
    _from
    0.85
     från
    0.85
    .from
    0.85
     từ
    0.84
    From
    0.80
    Activations Density 3.817%

    No Known Activations