INDEX

Explanations

code snippets or structures related to programming functions and object-oriented programming themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 GOODMAN

-0.16

 Goodman

-0.16

zia

-0.16

onas

-0.15

Ð¿Ð¾Ð½

-0.15

zs

-0.15

zej

-0.15

imat

-0.14

ullo

-0.14

á»ĵ

-0.14

POSITIVE LOGITS

werk

0.14

iniz

0.14

_Instance

0.14

 initialise

0.14

 setup

0.14

 Benedict

0.13

_SIGNATURE

0.13

 Ø§Ø±Ø´Ø¯

0.13

_initialized

0.13

íĺģ

0.13

Activations Density 0.063%

code snippets or structures related to programming functions and object-oriented programming themes

No Comments

No Known Activations