INDEX

Explanations

verbs related to making choices or selections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

è²¸

-0.14

ÅĻi

-0.14

licken

-0.14

lek

-0.14

VID

-0.14

NX

-0.14

ultipart

-0.13

IED

-0.13

âķĹ

-0.13

½

-0.13

POSITIVE LOGITS

 against

0.25

-in

0.25

-out

0.24

 into

0.23

-IN

0.22

imize

0.22

into

0.21

 instead

0.21

against

0.19

 Against

0.19

Activations Density 0.010%

verbs related to making choices or selections

No Comments

No Known Activations