INDEX

Explanations

references to the concept of "base" 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

sla

-0.19

sov

-0.17

naire

-0.17

feas

-0.16

sp

-0.16

ats

-0.16

sh

-0.16

hare

-0.15

acity

-0.15

ride

-0.15

POSITIVE LOGITS

/base

0.23

-base

0.20

(base

0.17

base

0.17

cover

0.16

yonel

0.16

alone

0.15

.base

0.15

 Unidos

0.15

brook

0.15

Activations Density 0.031%

references to the concept of "base" in various contexts

No Comments

No Known Activations