INDEX

Explanations

references to specific geographical locations and names

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

 Reconstruction

-0.15

jen

-0.15

ather

-0.15

á»ħ

-0.15

avers

-0.14

 Laud

-0.14

 Mand

-0.14

ira

-0.14

gee

-0.14

wyn

-0.13

POSITIVE LOGITS

pike

0.17

_IL

0.16

-lfs

0.15

ï»¿#

0.15

.BLL

0.15

agu

0.15

Ø¹ÙĦÙĪÙħØ§Øª

0.15

ahat

0.14

GuidId

0.14

ãĥĥãĤ«ãĥ¼

0.14

Activations Density 0.331%

references to specific geographical locations and names

No Comments

No Known Activations