INDEX

Explanations

references to individuals, particularly in a context related to positions or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

iaux

-0.15

lbrace

-0.14

ccione

-0.14

ervas

-0.14

bsite

-0.14

lanma

-0.13

ëĶĶìĭľ

-0.13

ÄĲT

-0.13

Ã©rica

-0.13

ParameterValue

-0.13

POSITIVE LOGITS

iod

0.28

eed

0.26

ivid

0.26

bard

0.26

ird

0.26

 Gord

0.25

ãĥ«ãĥī

0.25

ead

0.25

aid

0.25

ued

0.25

Activations Density 0.483%

references to individuals, particularly in a context related to positions or titles

No Comments

No Known Activations