INDEX

Explanations

references to clothing, especially t-shirts with slogans or symbols

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

$__

-0.15

usize

-0.14

à¸ł

-0.14

 WARRANTY

-0.14

::*

-0.14

rick

-0.14

reon

-0.14

 ì°©

-0.13

reck

-0.13

erland

-0.13

POSITIVE LOGITS

 reads

0.24

 words

0.23

 saying

0.21

 Reads

0.20

 text

0.20

 inscription

0.20

 wording

0.20

 slogan

0.20

 message

0.19

words

0.19

Activations Density 0.224%

references to clothing, especially t-shirts with slogans or symbols

No Comments

No Known Activations