INDEX

Explanations

occurrences of commas in the text

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

eux

-0.19

 THEM

-0.17

them

-0.17

 Ð½Ð¸Ñħ

-0.16

lui

-0.15

 Ð½ÑĮÐ¾Ð³Ð¾

-0.15

 ragaz

-0.14

 them

-0.14

 ØŃØ§ÙĦÛĮ

-0.14

 Ð½ÐµÐ³Ð¾

-0.13

POSITIVE LOGITS

 there

0.50

it

0.46

we

0.35

there

0.35

 they

0.28

you

0.26

 many

0.26

 ÙģØ¥ÙĨ

0.25

,it

0.25

 nothing

0.25

Activations Density 0.501%

occurrences of commas in the text

No Comments

No Known Activations