INDEX

Explanations

terms related to governmental and institutional frameworks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ayÄ±n

-0.16

uite

-0.16

 Berm

-0.15

uars

-0.15

Ð»Ð¸Ñĩ

-0.14

ukkit

-0.14

bounds

-0.13

pearance

-0.13

ãĥ¬ãĥĥãĥĪ

-0.13

eners

-0.13

POSITIVE LOGITS

al

1.54

AL

0.68

aliz

0.66

aln

0.65

alist

0.62

ally

0.59

als

0.53

ality

0.52

alis

0.48

alte

0.48

Activations Density 0.146%

terms related to governmental and institutional frameworks

No Comments

No Known Activations

terms related to governmental and institutional frameworks

No Comments

No Known Activations