INDEX

Explanations

repeated instances of the word "for" in various contexts, suggesting a focus on iterations or loops in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

assen

-0.14

CORD

-0.14

uren

-0.14

 safeguard

-0.14

agues

-0.14

 Î¼Î·Î½

-0.14

eguard

-0.13

ARING

-0.13

ÐºÐ¾Ð´

-0.13

cord

-0.13

POSITIVE LOGITS

Î³Î¿Ïħ

0.15

olley

0.15

icone

0.14

apon

0.14

 gravid

0.14

allee

0.13

èĢĮ

0.13

ÎºÎ¹

0.13

Ð½Ð¾Ð¿

0.13

 Bundy

0.13

Activations Density 0.027%

repeated instances of the word "for" in various contexts, suggesting a focus on iterations or loops in programming

No Comments

No Known Activations