INDEX

Explanations

terms related to academic or formal discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ø§ÙħÙĦ

-0.15

anzi

-0.15

orsk

-0.15

ulta

-0.15

.wrap

-0.14

Mae

-0.13

an

-0.13

 Prospect

-0.13

inned

-0.13

POSITIVE LOGITS

ermann

0.17

iles

0.17

ston

0.16

Ð½Ð¸ÑĨÑĮ

0.15

edin

0.15

ichni

0.15

radu

0.15

kees

0.14

BufferData

0.14

chodu

0.14

Activations Density 0.018%

terms related to academic or formal discourse

No Comments

No Known Activations