INDEX

Explanations

instances of significant content or details 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Schn

-0.15

 Sunder

-0.15

Mun

-0.15

ly

-0.14

ahr

-0.14

arily

-0.14

Hem

-0.14

engu

-0.13

stag

-0.13

 Paramount

-0.13

POSITIVE LOGITS

oningen

0.17

nection

0.16

oje

0.16

0.15

 WithEvents

0.15

CCI

0.15

ÅĻad

0.14

gle

0.14

ednou

0.14

verb

0.13

Activations Density 0.329%

instances of significant content or details in various contexts

No Comments

No Known Activations