INDEX

Explanations

terms related to criticism and condemnation

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

Ð³Ð¸

-0.17

 bore

-0.15

ald

-0.15

ales

-0.15

-0.14

 Madness

-0.14

uckle

-0.14

iero

-0.14

 controlled

-0.14

POSITIVE LOGITS

acos

0.16

oise

0.16

 Zaman

0.15

ÙĪÙĬÙĥ

0.15

XL

0.15

ãĥ¼ãĥģ

0.15

ilent

0.14

atory

0.14

hur

0.14

IPA

0.14

Activations Density 0.072%

terms related to criticism and condemnation

No Comments

No Known Activations