INDEX

Explanations

references to academic studies and research findings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

deen

-0.18

 amen

-0.16

uil

-0.15

ang

-0.15

å¡ŀ

-0.14

 Bing

-0.13

shr

-0.13

@nate

-0.13

 exact

-0.13

inand

-0.13

POSITIVE LOGITS

å®¿

0.16

oxide

0.16

oro

0.15

à¤¾à¤¯à¤¦

0.15

ocks

0.14

ç²

0.14

æ¬¾

0.14

ATTLE

0.14

contres

0.14

Activations Density 0.113%

references to academic studies and research findings

No Comments

No Known Activations