INDEX

Explanations

phrases and words related to personal experience, assessment, and communication

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

gee

-0.16

SystemService

-0.16

quisitions

-0.14

Ð¾Ð»Ñı

-0.14

ÑĥÐ¶

-0.14

ux

-0.13

/trunk

-0.13

iaz

-0.13

tej

-0.13

MUX

-0.13

POSITIVE LOGITS

 ì§ģìłĳ

0.17

pta

0.16

 directly

0.15

 rather

0.15

rather

0.14

 Rather

0.14

.wikipedia

0.14

Bid

0.14

ived

0.14

ŀĭ

0.14

Activations Density 0.225%

phrases and words related to personal experience, assessment, and communication

No Comments

No Known Activations