INDEX

Explanations

occurrences and variations of the word "to."

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

hek

-0.17

oras

-0.16

sek

-0.16

bands

-0.15

ACS

-0.15

urv

-0.14

 Seks

-0.14

Ã¹a

-0.14

urai

-0.13

ego

-0.13

POSITIVE LOGITS

 Trey

0.13

dept

0.13

.Transparent

0.13

lify

0.13

DEPTH

0.13

.definition

0.13

 conserv

0.13

atham

0.13

ill

0.13

Activations Density 0.021%

occurrences and variations of the word "to."

No Comments

No Known Activations