INDEX

Explanations

the word "of" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ean

-0.18

olian

-0.16

 broad

-0.14

ÙĪÙĦÛĮ

-0.14

-bodied

-0.14

gua

-0.14

ordan

-0.14

 Broad

-0.14

olie

-0.13

pesan

-0.13

POSITIVE LOGITS

assel

0.16

UCH

0.15

íĴ

0.14

 Distrib

0.14

amento

0.14

udge

0.14

ien

0.14

 Brands

0.13

reach

0.13

 reducers

0.13

Activations Density 0.004%

the word "of" in various contexts

No Comments

No Known Activations