INDEX

Explanations

terms related to data access and network connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uly

-0.18

_Query

-0.16

isy

-0.16

ching

-0.16

serter

-0.16

sein

-0.15

vit

-0.15

outs

-0.15

éĥİ

-0.15

asset

-0.15

POSITIVE LOGITS

ing

0.22

ry

0.21

most

0.20

ed

0.19

point

0.17

-mounted

0.17

pane

0.16

stone

0.16

cott

0.16

0.15

Activations Density 0.144%

terms related to data access and network connections

No Comments

No Known Activations