INDEX

Explanations

nouns and specific descriptors related to quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 entire

-0.15

olver

-0.15

hea

-0.14

phere

-0.14

 /*!<

-0.14

ãĥ¼ãĥĵ

-0.14

-than

-0.13

edith

-0.13

ofs

-0.13

urve

-0.13

POSITIVE LOGITS

vell

0.16

nell

0.16

iliar

0.15

inet

0.15

 Ø¨ÙĪØ§Ø¨Ø©

0.15

eral

0.14

angan

0.14

ilon

0.13

ylon

0.13

ãĥ¼ãĥ³

0.13

Activations Density 0.013%

nouns and specific descriptors related to quantities

No Comments

No Known Activations