INDEX

Explanations

references to actions of bringing or moving something to a specific place or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

nev

-0.16

ntag

-0.16

 PROGMEM

-0.15

æ³¥

-0.15

loor

-0.14

InputBorder

-0.14

STYPE

-0.14

 Stadium

-0.14

rib

-0.14

ombres

-0.13

POSITIVE LOGITS

orte

0.17

ewe

0.16

ursion

0.16

Ð¾ÑģÐ¿

0.15

/assert

0.14

uele

0.14

affer

0.14

iyel

0.14

/tests

0.14

FILES

0.14

Activations Density 0.066%

references to actions of bringing or moving something to a specific place or context

No Comments

No Known Activations