INDEX

Explanations

references to specific tools, objects, or items in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ople

-0.18

oxide

-0.15

yang

-0.15

byn

-0.15

ox

-0.15

Eid

-0.14

Cow

-0.14

Inserted

-0.14

-insert

-0.14

oit

-0.13

POSITIVE LOGITS

ebra

0.19

ibu

0.18

lander

0.17

acin

0.16

FileChooser

0.16

ae

0.15

 McCorm

0.14

 takson

0.14

ensors

0.14

lasting

0.14

Activations Density 0.193%

references to specific tools, objects, or items in the text

No Comments

No Known Activations