INDEX

Explanations

terms related to comparative analysis and details in reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

auga

-0.16

.Accessible

-0.16

slaught

-0.15

usercontent

-0.15

_HERSHEY

-0.15

ysl

-0.15

isory

-0.14

istine

-0.14

ëŀĻ

-0.14

sku

-0.14

POSITIVE LOGITS

bes

0.16

IAS

0.16

ERV

0.15

oss

0.14

lcm

0.14

URA

0.14

cassert

0.14

achs

0.14

ebi

0.13

Bes

0.13

Activations Density 0.299%

terms related to comparative analysis and details in reports

No Comments

No Known Activations