INDEX

Explanations

content related to entertainment controversies, particularly those involving performances

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

kehr

-0.18

ensi

-0.17

occan

-0.17

 Ïį

-0.16

_WRAP

-0.16

orest

-0.16

inci

-0.16

ke

-0.15

kovi

-0.15

bilt

-0.14

POSITIVE LOGITS

 Ones

0.17

sod

0.17

0.16

OUCH

0.15

quan

0.14

Screenshot

0.14

Compat

0.14

quote

0.14

0.13

Activations Density 0.048%

content related to entertainment controversies, particularly those involving performances

No Comments

No Known Activations