INDEX

Explanations

references to external sources or citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Å¾en

-0.18

ulas

-0.17

uous

-0.17

ings

-0.16

Ø§ÙģØª

-0.16

ague

-0.16

ily

-0.15

 Ella

-0.15

fen

-0.15

aneous

-0.14

POSITIVE LOGITS

/ref

0.26

.Ref

0.25

uge

0.24

actoring

0.23

-ref

0.23

eree

0.22

ref

0.22

resher

0.22

(ref

0.21

UGE

0.21

Activations Density 0.016%

references to external sources or citations

No Comments

No Known Activations