INDEX

Explanations

numerical values associated with software versioning and configuration

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

'gc

-0.18

pository

-0.16

¬Ĥ

-0.15

ä¸Ģæ¬¡

-0.15

.IContainer

-0.14

CharCode

-0.14

antha

-0.14

è¸

-0.14

agra

-0.14

¹

-0.14

POSITIVE LOGITS

ç¾½

0.17

Ded

0.17

Signature

0.16

illon

0.15

 deductions

0.15

 Signature

0.15

ston

0.14

PIP

0.14

pac

0.14

illes

0.14

Activations Density 0.029%

numerical values associated with software versioning and configuration

No Comments

No Known Activations