INDEX

Explanations

statements presenting degrees of certainty or speculation about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

eb

-0.17

bject

-0.14

esar

-0.14

locking

-0.13

das

-0.13

\/

-0.13

yny

-0.13

ci

-0.13

caff

-0.13

POSITIVE LOGITS

antha

0.18

allback

0.17

CustomLabel

0.16

 tá»Ļc

0.15

antan

0.15

à¸¸à¸¡

0.14

è¯Ŀ

0.14

bard

0.14

cou

0.14

forder

0.13

Activations Density 0.094%

statements presenting degrees of certainty or speculation about various subjects

No Comments

No Known Activations