INDEX

Explanations

actions and methods related to achievement and productivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Ð²Ð°

-0.16

á»ĵn

-0.15

ØªØ§ÙĨ

-0.15

ì½©

-0.14

aea

-0.14

markup

-0.14

otech

-0.14

dx

-0.14

eka

-0.13

POSITIVE LOGITS

ings

0.18

stein

0.17

ÂŃing

0.15

ÑĢÐ¸Ñģ

0.15

lez

0.14

 otherwise

0.14

ollo

0.14

ingly

0.14

hol

0.14

itr

0.14

Activations Density 0.227%

actions and methods related to achievement and productivity

No Comments

No Known Activations