INDEX

Explanations

the occurrences of the word "to" 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ampie

-0.14

enever

-0.14

 playable

-0.14

ãĥ³ãĥĶ

-0.14

åĦª

-0.14

ijo

-0.13

-report

-0.13

asin

-0.13

ÑĤÑı

-0.13

ETCH

-0.13

POSITIVE LOGITS

PLICIT

0.15

eyim

0.14

agens

0.14

.mount

0.14

ãģ©ãģĵ

0.14

 Coleman

0.14

.TryParse

0.14

.wind

0.13

çĴĥ

0.13

inx

0.13

Activations Density 0.069%

the occurrences of the word "to" in various contexts

No Comments

No Known Activations