INDEX

Explanations

descriptors of significance and impact, particularly relating to popularity or success

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

THR

-0.16

anos

-0.16

ICY

-0.15

gal

-0.15

cken

-0.15

ali

-0.15

egal

-0.14

fos

-0.14

igin

-0.14

usic

-0.14

POSITIVE LOGITS

lisi

0.14

adin

0.14

 ones

0.14

Ø§ÙĪØª

0.14

 cris

0.14

among

0.14

 posible

0.14

VERR

0.14

yet

0.13

InThe

0.13

Activations Density 0.087%

descriptors of significance and impact, particularly relating to popularity or success

No Comments

No Known Activations