INDEX

Explanations

references to specific decision-making processes and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

(æĹ¥

-0.13

hei

-0.13

ëŀį

-0.13

htags

-0.13

 sice

-0.13

REET

-0.12

arella

-0.12

(æľĪ

-0.12

okane

-0.12

POSITIVE LOGITS

she

0.18

 they

0.18

her

0.16

ï

0.15

his

0.14

 them

0.14

 elle

0.14

 [âĢ¦

0.14

 their

0.14

 They

0.14

Activations Density 8.735%

references to specific decision-making processes and actions

No Comments

No Known Activations