INDEX

Explanations

phrases indicating the provision or availability of detailed information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

INLINE

-0.15

 Bryan

-0.15

vrier

-0.15

 addCriterion

-0.14

ulant

-0.14

 migrationBuilder

-0.14

dol

-0.13

 place

-0.13

 Schn

-0.13

Related

-0.13

POSITIVE LOGITS

thon

0.15

ood

0.15

bay

0.14

verse

0.14

 prÅ¯bÄĽhu

0.14

ole

0.14

bove

0.14

ensing

0.14

arem

0.14

Ð¼Ñĸ

0.14

Activations Density 0.082%

phrases indicating the provision or availability of detailed information

No Comments

No Known Activations