INDEX

Explanations

references to alphabetical categorization or listings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

PEC

-0.15

il

-0.14

 Ð¾Ð±Ð¾ÑĢ

-0.14

union

-0.14

áº¥p

-0.13

Cow

-0.13

pics

-0.13

lict

-0.13

 tracking

-0.13

Å¾il

-0.13

POSITIVE LOGITS

.scalablytyped

0.17

/gtest

0.16

.LayoutStyle

0.15

AFX

0.15

_deinit

0.15

cctor

0.15

AlmostEqual

0.14

ecut

0.14

.viewer

0.14

ctime

0.14

Activations Density 0.006%

references to alphabetical categorization or listings

No Comments

No Known Activations