INDEX

Explanations

references to the term "Golden," which appears in various contexts throughout the document

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

noch

-0.17

igr

-0.17

les

-0.17

ual

-0.16

apon

-0.16

iah

-0.15

vin

-0.15

ata

-0.15

shint

-0.15

ivals

-0.15

POSITIVE LOGITS

rod

0.32

 retrie

0.28

rule

0.19

ratio

0.19

 opportunity

0.18

golden

0.18

baum

0.18

berg

0.18

 Retrie

0.18

eye

0.17

Activations Density 0.008%

references to the term "Golden," which appears in various contexts throughout the document

No Comments

No Known Activations