INDEX

Explanations

punctuation marks and formatting variations within 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

pil

-0.16

atego

-0.15

ppo

-0.15

 Harrison

-0.15

pell

-0.15

ami

-0.15

hyp

-0.15

Ã¢m

-0.14

hyp

-0.14

rangle

-0.14

POSITIVE LOGITS

anter

0.18

iglia

0.15

ç£

0.15

itre

0.15

elerik

0.14

oth

0.14

prs

0.14

 Pages

0.14

shade

0.13

 Trident

0.13

Activations Density 0.060%

punctuation marks and formatting variations within the text

No Comments

No Known Activations