INDEX

Explanations

spatial directions and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

AZE

-0.16

emi

-0.16

-0.15

anky

-0.15

-0.14

¶

-0.14

id

-0.14

ìłľ

-0.14

incr

-0.14

inh

-0.14

POSITIVE LOGITS

-hand

0.24

 corner

0.23

 corners

0.20

corner

0.19

most

0.18

 ÑģÑĤÐ¾ÑĢÐ¾Ð½Ñĥ

0.18

_corner

0.17

 Rune

0.16

 Corner

0.15

-corner

0.15

Activations Density 0.030%

spatial directions and locations

No Comments

No Known Activations