INDEX

Explanations

instances of the word "pretend" and variations of it in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

jack

-0.16

á»ħ

-0.15

ëŀ

-0.15

fang

-0.15

Bor

-0.14

apers

-0.14

oden

-0.14

å¥ĩ

-0.14

hed

-0.14

aper

-0.14

POSITIVE LOGITS

nego

0.15

ÑĦÐ¸

0.15

pid

0.14

hle

0.14

misc

0.14

 quot

0.14

lesai

0.14

ugeot

0.14

anggan

0.13

 gravity

0.13

Activations Density 0.020%

instances of the word "pretend" and variations of it in various contexts

No Comments

No Known Activations