INDEX

Explanations

forms of verbs and their derivations, particularly focusing on past tense and gerunds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

lett

-0.15

ware

-0.15

inÃ§

-0.14

 VÅ¡ech

-0.14

UTE

-0.14

á»§i

-0.14

èªĮ

-0.14

slu

-0.14

unya

-0.13

à¸ģ

-0.13

POSITIVE LOGITS

tas

0.15

Hol

0.15

orious

0.15

uras

0.14

ÑīÐ¸Ðµ

0.14

Ø²ÙĬØ¯

0.13

aan

0.13

Rob

0.13

sum

0.13

edian

0.13

Activations Density 0.629%

forms of verbs and their derivations, particularly focusing on past tense and gerunds

No Comments

No Known Activations