INDEX

Explanations

instances of the word "for" and its variations, as well as contexts indicating conditions, expectations, and predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

raki

-0.16

iguiente

-0.15

ihilation

-0.15

lut

-0.14

ehen

-0.14

Î¼Î¿Î¯

-0.14

MAL

-0.14

ownik

-0.14

.staff

-0.14

apus

-0.14

POSITIVE LOGITS

 Humph

0.15

Fle

0.15

ESCO

0.15

å©·

0.14

ero

0.14

yw

0.14

TRACT

0.14

VEN

0.14

SUMER

0.14

 dotted

0.14

Activations Density 0.000%

instances of the word "for" and its variations, as well as contexts indicating conditions, expectations, and predictions

No Comments

No Known Activations