INDEX

Explanations

punctuation marks and special characters indicating emphasis or dialogue

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

Î¬Ïĥ

-0.16

imas

-0.15

IRT

-0.15

ë°ľ

-0.15

-Semit

-0.14

ynomial

-0.14

eka

-0.14

Ð²Ð°ÑĢ

-0.14

fo

-0.14

ÑģÐ»Ð¸

-0.14

POSITIVE LOGITS

0.27

0.24

0.23

Activations Density 0.039%

punctuation marks and special characters indicating emphasis or dialogue

No Comments

No Known Activations