INDEX

Explanations

references to the word "golden" or its variations in different contexts

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

igr

-0.18

noch

-0.17

les

-0.16

iah

-0.15

ual

-0.15

vin

-0.15

apon

-0.15

¸ı

-0.14

ivals

-0.14

POSITIVE LOGITS

rod

0.32

 retrie

0.28

rule

0.21

berg

0.19

 opportunity

0.19

 rule

0.19

eye

0.18

 Rule

0.18

-rule

0.18

 Retrie

0.17

Activations Density 0.008%

references to the word "golden" or its variations in different contexts

No Comments

No Known Activations