INDEX

Explanations

questions and phrases indicating personal inquiries or reflections

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

rouw

-0.15

PAN

-0.15

wit

-0.14

uga

-0.14

stddef

-0.14

enna

-0.14

Clo

-0.14

ç¼ĺ

-0.14

æĸ½

-0.14

edException

-0.13

POSITIVE LOGITS

.scalablytyped

0.15

jam

0.15

geme

0.14

lesai

0.14

 ìĿĢ

0.14

ulet

0.14

¶Ī

0.14

tae

0.13

 silver

0.13

_Module

0.13

Activations Density 0.199%

questions and phrases indicating personal inquiries or reflections

No Comments

No Known Activations