INDEX

Explanations

function declarations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

setFlash

-0.17

arde

-0.17

zung

-0.15

á»Ń

-0.15

egree

-0.14

phin

-0.14

_RPC

-0.14

rophe

-0.14

arda

-0.14

 Fulton

-0.14

POSITIVE LOGITS

/Foundation

0.17

enery

0.15

Ð´Ð°Ð¼

0.14

LLU

0.14

 å£

0.14

andr

0.14

 ãģª

0.14

extView

0.13

igin

0.13

ENSITY

0.13

Activations Density 0.012%

function declarations

No Comments

No Known Activations