INDEX

Explanations

references to placeholder pages or utility functions related to user content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

icone

-0.18

reur

-0.18

ccione

-0.17

apia

-0.16

atoria

-0.15

orgia

-0.15

arih

-0.14

ubern

-0.14

 diseÃ±ador

-0.14

.STATE

-0.13

POSITIVE LOGITS

ust

0.16

eds

0.16

 tempor

0.16

och

0.15

hall

0.15

eted

0.15

inne

0.15

umi

0.14

Activations Density 0.006%

references to placeholder pages or utility functions related to user content

No Comments

No Known Activations