INDEX

Explanations

XML or HTML tags related to scope and dependencies

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

UGH

-0.16

Î³Îµ

-0.15

AAA

-0.15

igr

-0.15

ovel

-0.14

coh

-0.14

avigator

-0.14

illo

-0.14

plorer

-0.14

engan

-0.14

POSITIVE LOGITS

0.15

 verd

0.14

ahas

0.14

ombo

0.14

imd

0.14

Gi

0.13

ustos

0.13

Activations Density 0.005%

XML or HTML tags related to scope and dependencies

No Comments

No Known Activations