INDEX

Explanations

terms related to heightened emotional experiences or dramatic occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ibern

-0.17

lew

-0.16

unn

-0.15

 Loot

-0.15

iloc

-0.14

agnar

-0.14

uters

-0.14

-way

-0.14

ÑģÑıÑĤ

-0.14

 cent

-0.13

POSITIVE LOGITS

ively

0.17

 Ð´ÐµÐ»Ðµ

0.15

argo

0.15

IBUTES

0.14

alore

0.14

ecute

0.14

nil

0.14

eu

0.13

oca

0.13

ei

0.13

Activations Density 0.012%

terms related to heightened emotional experiences or dramatic occurrences

No Comments

No Known Activations