INDEX

Explanations

locations and specific place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Wein

-0.16

 Epstein

-0.15

zel

-0.15

APS

-0.15

aps

-0.15

""

-0.14

uese

-0.14

zo

-0.14

ebe

-0.14

ACS

-0.13

POSITIVE LOGITS

iku

0.16

æ¡

0.16

ilty

0.15

ingleton

0.15

_cmos

0.15

InlineData

0.15

PTY

0.15

KHTML

0.14

ë²Į

0.14

.GetInt

0.14

Activations Density 0.063%

locations and specific place names

No Comments

No Known Activations