INDEX

Explanations

phrases or references related to specific experiences or personal opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

raisal

-0.16

eer

-0.15

aze

-0.13

 ÑĤÐ°Ð¹

-0.13

actal

-0.13

ÄĲT

-0.13

å²

-0.13

ugal

-0.12

_mappings

-0.12

POSITIVE LOGITS

nbsp

0.17

gether

0.15

ovan

0.15

Â·

0.15

bidden

0.14

NAL

0.14

dependence

0.13

/std

0.13

lf

0.13

ARRANT

0.13

Activations Density 0.970%

phrases or references related to specific experiences or personal opinions

No Comments

No Known Activations