INDEX

Explanations

occurrences of the letter 'K' 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 @ 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

à¸£

-0.17

onta

-0.17

ÑĢÑĸÐ¼

-0.17

ÑĢÐ°

-0.17

yle

-0.16

Ø§ÙĨ

-0.16

Ð¾ÑĢ

-0.16

ÏĮ

-0.16

ro

-0.15

ignum

-0.15

POSITIVE LOGITS

oni

0.19

vant

0.17

DJ

0.17

holm

0.17

hand

0.16

eb

0.16

hat

0.16

linger

0.16

lint

0.16

Activations Density 0.095%

occurrences of the letter 'K' in various contexts

No Comments

No Known Activations