INDEX

Explanations

forms of the verb "do" and related phrases that indicate actions or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

calls

-0.15

ÐºÑĥÑĢ

-0.15

 æ¨

-0.15

loquent

-0.14

byterian

-0.13

tributes

-0.13

)((((

-0.13

 zoekt

-0.13

EMS

-0.13

oli

-0.13

POSITIVE LOGITS

ze

0.18

Spark

0.15

omba

0.15

Ã¡c

0.15

 Spark

0.14

 magic

0.14

zens

0.14

lÃ¡n

0.13

illet

0.13

 Paula

0.13

Activations Density 0.209%

forms of the verb "do" and related phrases that indicate actions or activities

No Comments

No Known Activations