INDEX

Explanations

mentions of media figures and television programs in the context of discussions or interviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

agas

-0.16

ads

-0.15

 Rudd

-0.15

Ø¨Ø·

-0.15

oot

-0.15

 Nexus

-0.15

Pri

-0.14

ague

-0.14

resher

-0.14

 Nest

-0.14

POSITIVE LOGITS

aea

0.16

 MethodInfo

0.15

ciler

0.15

strip

0.15

urette

0.14

UIScreen

0.14

 Gins

0.14

cia

0.14

lore

0.13

ayah

0.13

Activations Density 0.039%

mentions of media figures and television programs in the context of discussions or interviews

No Comments

No Known Activations