INDEX

Explanations

expressions indicating similarities or commonality among subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

VENT

-0.15

swick

-0.13

PURE

-0.13

ku

-0.13

 Ð¾ÑģÐ½Ð¾Ð²Ð½Ð¾Ð¼

-0.13

stellung

-0.13

iest

-0.13

es

-0.13

ovie

-0.13

POSITIVE LOGITS

0.15

vron

0.15

	volatile

0.15

ï¸ı

0.14

ħn

0.14

utzer

0.14

 chaud

0.13

irk

0.13

udo

0.13

iao

0.13

Activations Density 0.129%

expressions indicating similarities or commonality among subjects

No Comments

No Known Activations