INDEX

Explanations

references to the English language and its speakers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

eh

-0.16

achel

-0.15

adol

-0.14

hall

-0.14

eut

-0.14

ech

-0.14

hq

-0.14

à¸ļà¸ļ

-0.14

acious

-0.14

Ð»Ð¸Ð½Ð¸

-0.13

POSITIVE LOGITS

-speaking

0.16

izar

0.15

Č↵

0.15

WER

0.14

æĻ´

0.14

(es

0.14

Void

0.14

RenderTarget

0.14

cent

0.14

Activations Density 0.022%

references to the English language and its speakers

No Comments

No Known Activations