INDEX

Explanations

mentions of semi-related terms or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

-0.14

unger

-0.14

 Kendrick

-0.14

chn

-0.14

umm

-0.13

iem

-0.13

ank

-0.13

Hor

-0.13

iating

-0.13

POSITIVE LOGITS

peater

0.15

Dob

0.15

roud

0.15

warm

0.15

CJK

0.15

AGMA

0.15

endoza

0.14

dac

0.14

ocode

0.14

ville

0.14

Activations Density 0.016%

mentions of semi-related terms or concepts

No Comments

No Known Activations