INDEX

Explanations

words and phrases related to existence and identity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Volt

-0.16

owi

-0.15

volt

-0.15

iese

-0.14

CAST

-0.14

idl

-0.14

wert

-0.14

 Barnett

-0.13

dig

-0.13

Dig

-0.13

POSITIVE LOGITS

iston

0.16

 ******************************************************************************↵

0.16

ãģĴ

0.15

á»ķ

0.15

iale

0.15

ione

0.14

urette

0.14

ordan

0.14

ording

0.14

ram

0.14

Activations Density 0.062%

words and phrases related to existence and identity

No Comments

No Known Activations