INDEX

Explanations

professions and roles within 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 @ 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

AGMA

-0.17

 USHORT

-0.16

ÑĦÑĸ

-0.15

agma

-0.15

extField

-0.15

gend

-0.14

generation

-0.14

pliers

-0.14

iets

-0.14

occupied

-0.14

POSITIVE LOGITS

who

0.24

 whose

0.18

oki

0.18

who

0.16

 extra

0.16

toMatch

0.16

cum

0.15

 active

0.15

at

0.14

 whom

0.14

Activations Density 0.049%

professions and roles within various contexts

No Comments

No Known Activations