INDEX

Explanations

instances of punctuation marks, particularly 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

aku

-0.21

egen

-0.17

urai

-0.16

estone

-0.15

_SUBJECT

-0.14

ÐµÐ»ÑĮÐ·Ñı

-0.14

 Strat

-0.14

bold

-0.14

ÑıÑĩ

-0.14

uggy

-0.14

POSITIVE LOGITS

ollen

0.18

addon

0.16

essler

0.15

ancias

0.15

spr

0.15

Scaler

0.14

mdi

0.14

ap

0.13

ÐĴÐŀ

0.13

Activations Density 0.023%

instances of punctuation marks, particularly commas, in the text

No Comments

No Known Activations