INDEX

Explanations

phrases indicating sensitivity and responsiveness to external influences or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ORED

-0.17

weit

-0.16

CLUDING

-0.15

ermann

-0.15

ëĭĿ

-0.15

ovsky

-0.14

TRL

-0.14

cac

-0.14

CHAIN

-0.13

ÑĢÐ¾Ð²Ð¾Ð´

-0.13

POSITIVE LOGITS

Sac

0.15

Fol

0.14

 Vault

0.14

èĩªèº«

0.14

 mistress

0.14

fol

0.13

esa

0.13

rec

0.13

 quanto

0.13

Activations Density 0.155%

phrases indicating sensitivity and responsiveness to external influences or conditions

No Comments

No Known Activations