INDEX

Explanations

terms indicating ambiguity or lack of specificity

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

agma

-0.16

raman

-0.16

ÐĲÑĢÑħÑĸÐ²

-0.15

re

-0.15

DataExchange

-0.15

nr

-0.15

zet

-0.14

.scalablytyped

-0.14

ëĭ¥

-0.14

uced

-0.13

POSITIVE LOGITS

EST

0.15

ey

0.15

eyen

0.14

eye

0.14

olini

0.14

extent

0.14

ÙĭØ§

0.13

Î»Ïī

0.13

Activations Density 0.005%

terms indicating ambiguity or lack of specificity

No Comments

No Known Activations