INDEX

Explanations

coding elements and structures typically found in templates or HTML-like syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 abnormal

-0.15

.qq

-0.15

endas

-0.15

\admin

-0.14

ï»¿↵↵

-0.14

lom

-0.14

:normal

-0.14

akk

-0.14

fs

-0.14

avad

-0.13

POSITIVE LOGITS

ctal

0.17

ego

0.16

 tick

0.15

apos

0.14

wheel

0.14

 kÃªnh

0.14

oub

0.14

iben

0.14

esson

0.14

Activations Density 0.002%

coding elements and structures typically found in templates or HTML-like syntax

No Comments

No Known Activations