INDEX

Explanations

names or titles related to leadership or significant roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

elf

-0.19

DEM

-0.17

-0.15

æ»ħ

-0.14

presso

-0.14

ibar

-0.14

resh

-0.14

reen

-0.14

ynthesis

-0.14

cret

-0.13

POSITIVE LOGITS

apore

0.16

-pr

0.16

iples

0.16

urat

0.16

asti

0.15

ordial

0.15

pr

0.15

Cog

0.15

ounced

0.15

-Ð¿ÑĢÐ°Ð²

0.15

Activations Density 0.027%

names or titles related to leadership or significant roles

No Comments

No Known Activations