INDEX

Explanations

discussions about challenges and tasks 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

zend

-0.17

KD

-0.15

kili

-0.15

illez

-0.15

uya

-0.15

fone

-0.14

rift

-0.14

_exchange

-0.14

harma

-0.14

avar

-0.14

POSITIVE LOGITS

 swallow

0.15

WithError

0.15

¹

0.15

task

0.15

 task

0.15

roman

0.14

ProgressHUD

0.14

 TASK

0.14

-task

0.13

_attempt

0.13

Activations Density 0.321%

discussions about challenges and tasks in various contexts

No Comments

No Known Activations