INDEX

Explanations

references to the name "Jackson" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ustin

-0.15

UX

-0.15

ux

-0.15

WAY

-0.14

ager

-0.14

uck

-0.14

idon

-0.14

erta

-0.14

geh

-0.14

okies

-0.14

POSITIVE LOGITS

 Hole

0.23

hole

0.23

 hole

0.19

ville

0.19

.databind

0.18

ian

0.17

VILLE

0.17

-hole

0.17

EMC

0.16

sik

0.16

Activations Density 0.010%

references to the name "Jackson" in various contexts

No Comments

No Known Activations