INDEX

Explanations

references to the term "advanced" 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

soever

-0.21

lers

-0.17

/do

-0.17

NAMESPACE

-0.16

laus

-0.16

hots

-0.15

 Flesh

-0.15

ulary

-0.15

mers

-0.15

enames

-0.15

POSITIVE LOGITS

-stage

0.23

antages

0.23

-placement

0.21

 Placement

0.21

ancement

0.19

 notice

0.19

Placement

0.19

 stages

0.19

-degree

0.18

/exp

0.18

Activations Density 0.033%

references to the term "advanced" in various contexts

No Comments

No Known Activations