INDEX

Explanations

references to boundaries or edges associated with objects or spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ulerAngles

-0.17

jour

-0.15

iele

-0.15

OrCreate

-0.15

SqlServer

-0.15

HEET

-0.15

lops

-0.15

bow

-0.14

vla

-0.14

LECT

-0.14

POSITIVE LOGITS

zung

0.15

 strips

0.14

çĻ¾

0.14

istar

0.14

oves

0.14

unj

0.14

 çĻ¾

0.14

acias

0.14

unding

0.14

/base

0.14

Activations Density 0.015%

references to boundaries or edges associated with objects or spaces

No Comments

No Known Activations