INDEX

Explanations

instances of the word "to" used 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 @ 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

contres

-0.17

_Framework

-0.16

ternet

-0.15

ÅĦst

-0.15

ald

-0.15

TimeString

-0.14

/TT

-0.14

/framework

-0.14

openh

-0.14

aminer

-0.14

POSITIVE LOGITS

DO

0.16

ook

0.16

asty

0.15

0.14

lb

0.14

ephy

0.14

/articles

0.14

Activations Density 0.421%

instances of the word "to" used in various contexts

No Comments

No Known Activations