INDEX

Explanations

words related to legislative processes and quantitative data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

thag

-0.16

elia

-0.16

 Killer

-0.14

xia

-0.14

iedy

-0.14

elpers

-0.14

aptcha

-0.13

.creator

-0.13

leaf

-0.13

croft

-0.13

POSITIVE LOGITS

empo

0.19

igue

0.15

col

0.15

ainen

0.14

Tra

0.14

atra

0.14

adel

0.14

ÑĤÐµÐ½

0.14

 genre

0.14

ÑĤÐ°Ð¶

0.14

Activations Density 0.544%

words related to legislative processes and quantitative data

No Comments

No Known Activations