INDEX

Explanations

specific personal names and attributes related to individuals or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

leton

-0.15

cheon

-0.14

arrow

-0.14

 offic

-0.14

-0.13

enne

-0.13

eff

-0.13

 mach

-0.13

ead

-0.13

POSITIVE LOGITS

atre

0.16

.CG

0.14

amic

0.14

_Err

0.14

FI

0.13

_REV

0.13

><?

0.13

wart

0.13

IDb

0.13

ULATE

0.13

Activations Density 1.140%

specific personal names and attributes related to individuals or events

No Comments

No Known Activations