INDEX

Explanations

HTML attributes in the document

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

 Naming

-0.15

annes

-0.13

uele

-0.13

erre

-0.13

Br

-0.13

 digit

-0.13

exc

-0.13

itest

-0.13

POSITIVE LOGITS

æĸ¹åĲĳ

0.14

CHASE

0.14

bang

0.14

ocation

0.14

#ab

0.14

Formation

0.14

/pages

0.13

Å©i

0.13

ginas

0.13

@update

0.13

Activations Density 0.004%

HTML attributes in the document

No Comments

No Known Activations