INDEX

Explanations

phrases related to employment benefits and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

iedy

-0.15

LOPT

-0.15

efs

-0.15

UCH

-0.14

Ð¾ÑĩÐºÐ¸

-0.14

prs

-0.14

ãĤ·ãĥ¼

-0.14

iaz

-0.14

Ð¾ÑĩÐµÐº

-0.14

oggler

-0.14

POSITIVE LOGITS

0.15

 McCorm

0.14

int

0.13

uste

0.13

ĳ

0.12

RectTransform

0.12

 behind

0.12

 exclus

0.12

Activations Density 0.397%

phrases related to employment benefits and policies

No Comments

No Known Activations