INDEX

Explanations

mentioned names and titles associated with significant roles or identities

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

bid

-0.15

htt

-0.14

uche

-0.14

tell

-0.13

tran

-0.13

ł

-0.13

-imm

-0.13

gc

-0.13

 pylint

-0.13

 Edition

-0.12

POSITIVE LOGITS

 ayrÄ±ca

0.16

elize

0.16

lien

0.16

Ð¾Ð»Ð°Ð³

0.15

 ÙĩÙħÚĨÙĨÛĮÙĨ

0.14

essed

0.14

 Philipp

0.14

ERGE

0.14

reu

0.13

_OM

0.13

Activations Density 0.193%

mentioned names and titles associated with significant roles or identities

No Comments

No Known Activations