INDEX

Explanations

references to locations or contexts involving "back" or "rear."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

VID

-0.15

peria

-0.15

pery

-0.15

ÑĢÐ¸

-0.15

LOCK

-0.15

anges

-0.15

IZED

-0.14

ucc

-0.14

jer

-0.14

POSITIVE LOGITS

/back

0.30

(back

0.24

=back

0.22

/front

0.22

side

0.21

.Back

0.19

scatter

0.18

country

0.18

slash

0.18

space

0.17

Activations Density 0.031%

references to locations or contexts involving "back" or "rear."

No Comments

No Known Activations