INDEX

Explanations

references to newness or updates regarding information or products

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

iras

-0.15

yon

-0.14

glich

-0.14

 Parr

-0.14

Chr

-0.14

ungle

-0.14

bbe

-0.14

ocache

-0.13

uite

-0.13

 Griffith

-0.13

POSITIVE LOGITS

esthes

0.15

rit

0.15

Responder

0.14

anj

0.14

 SPDX

0.14

ÐĺÐ¢

0.13

 pháºŃn

0.13

aza

0.13

/feed

0.13

oop

0.13

Activations Density 0.517%

references to newness or updates regarding information or products

No Comments

No Known Activations