INDEX

Explanations

specific image file names and references within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

actus

-0.18

 poll

-0.16

lian

-0.16

oj

-0.15

ismatch

-0.14

ubbo

-0.14

.cx

-0.14

uj

-0.14

orable

-0.14

POSITIVE LOGITS

.yy

0.19

ipes

0.19

 æĴ

0.15

ensem

0.15

.PerformLayout

0.14

Ã§os

0.14

 dignity

0.14

ÙĬÙĪÙĨ

0.14

à¹ģà¸ª

0.14

 ÑĤÐ¾Ð²

0.14

Activations Density 0.018%

specific image file names and references within the text

No Comments

No Known Activations