INDEX

Explanations

punctuation and sentence endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

odore

-0.15

warts

-0.14

ç¦

-0.14

entine

-0.14

urile

-0.13

ØŃÙĦ

-0.13

isme

-0.13

ercise

-0.13

haar

-0.13

ernes

-0.13

POSITIVE LOGITS

ETS

0.16

oug

0.16

csi

0.15

liqu

0.15

annon

0.15

afka

0.15

aukee

0.14

claim

0.14

esor

0.14

 termin

0.14

Activations Density 0.000%

punctuation and sentence endings

No Comments

No Known Activations