INDEX

Explanations

punctuation marks and their patterns 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 @ 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

ÏĦÎ¶

-0.15

chie

-0.13

ishi

-0.13

éľ²

-0.13

icha

-0.13

ãģĵãĤį

-0.13

 ÑģÐ¼

-0.13

ãģ«ãģ¤

-0.13

ÏĥÎ¼

-0.13

baugh

-0.13

POSITIVE LOGITS

atten

0.15

_weak

0.14

orsk

0.14

ryn

0.14

rdf

0.14

 versa

0.14

ynch

0.14

Ð¾Ð»Ð°Ð³

0.13

arih

0.13

bens

0.13

Activations Density 0.002%

punctuation marks and their patterns in the text

No Comments

No Known Activations