INDEX

Explanations

phrases or structures that involve emphasis on "the" and other related elements in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ergy

-0.14

ortal

-0.13

*>*

-0.13

anything

-0.13

 Translation

-0.13

ingroup

-0.13

arro

-0.13

itar

-0.12

Staff

-0.12

icum

-0.12

POSITIVE LOGITS

à¸ģà¸£à¸£à¸¡

0.15

enge

0.15

 ability

0.14

lage

0.14

uario

0.14

erken

0.14

fec

0.14

andard

0.13

lj

0.13

eda

0.13

Activations Density 0.057%

phrases or structures that involve emphasis on "the" and other related elements in descriptions

No Comments

No Known Activations