INDEX

Explanations

instances of the word "edit" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.16

hardt

-0.15

ativity

-0.15

prit

-0.15

holds

-0.15

lege

-0.14

een

-0.14

áº¡ng

-0.14

POSITIVE LOGITS

ting

0.22

emd

0.17

(edit

0.16

è¼¯

0.16

elman

0.16

ied

0.16

TINGS

0.15

/view

0.15

/design

0.15

ì¦Ŀ

0.15

Activations Density 0.015%

instances of the word "edit" and its variations in different contexts

No Comments

No Known Activations