INDEX

Explanations

instances of the word "Hey."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

omic

-0.16

hyp

-0.15

-scale

-0.14

>\<

-0.14

ãģ«ãģ¨

-0.14

vale

-0.13

 emperor

-0.13

 Ramp

-0.13

 trÃº

-0.13

stav

-0.13

POSITIVE LOGITS

avin

0.16

áº¡n

0.15

æİª

0.15

Ø¦Øª

0.15

ocu

0.15

0.14

èº«

0.14

dna

0.14

Activations Density 0.013%

instances of the word "Hey."

No Comments

No Known Activations