INDEX

Explanations

actions and movements related to turning and direction changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rada

-0.16

kdir

-0.15

SPATH

-0.15

dera

-0.15

_SYS

-0.15

fono

-0.15

SystemService

-0.15

URLException

-0.15

ÅĻÃŃd

-0.14

fram

-0.14

POSITIVE LOGITS

0.16

 turn

0.14

atre

0.14

 /*!<

0.14

ikel

0.14

_mp

0.14

 Profit

0.14

Ãło

0.13

.gb

0.13

oretical

0.13

Activations Density 0.095%

actions and movements related to turning and direction changes

No Comments

No Known Activations