INDEX

Explanations

phrases indicating movement or direction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Acts

-0.14

lyph

-0.14

 intents

-0.14

igr

-0.13

Tw

-0.13

CCCCCC

-0.13

 Loren

-0.13

 canned

-0.13

iÃŃ

-0.13

POSITIVE LOGITS

mani

0.14

ivan

0.14

atos

0.14

ecies

0.14

å®Ļ

0.14

lasting

0.14

submitted

0.13

Ã¤nn

0.13

.FR

0.13

turnstile

0.13

Activations Density 0.041%

phrases indicating movement or direction

No Comments

No Known Activations