INDEX

Explanations

key issues or findings within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

beck

-0.17

ahr

-0.16

è¼Ķ

-0.14

dz

-0.13

 rebound

-0.13

ØªØ§Ø¨

-0.13

iscard

-0.13

utorials

-0.13

bcm

-0.12

 RectTransform

-0.12

POSITIVE LOGITS

 sentence

0.65

 sentences

0.60

 paragraph

0.60

sentence

0.52

 paragraphs

0.51

 Sentence

0.48

paragraph

0.47

 Paragraph

0.44

Sentence

0.43

entence

0.41

Activations Density 0.251%

key issues or findings within a document

No Comments

No Known Activations