INDEX

Explanations

the word "to" and its variations across different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.16

Ð²Ð¾Ð»Ñı

-0.15

 Rocky

-0.15

vine

-0.15

mouth

-0.15

erto

-0.14

 Rams

-0.14

ws

-0.14

elves

-0.14

udas

-0.14

POSITIVE LOGITS

kaÃ§

0.15

ubi

0.15

asser

0.14

ovny

0.14

 Hubb

0.13

ECH

0.13

.ov

0.13

azon

0.13

 brun

0.13

.RunWith

0.13

Activations Density 0.327%

the word "to" and its variations across different contexts

No Comments

No Known Activations