INDEX

Explanations

references to government or institutional support and collaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

upy

-0.15

iner

-0.15

ipop

-0.15

 revolution

-0.14

ssf

-0.14

shint

-0.14

poke

-0.14

 ÙħØŃÙĦ

-0.14

ige

-0.14

uffy

-0.14

POSITIVE LOGITS

 Ø§ÙĦØ£ÙħØ±ÙĬÙĥÙĬØ©

0.15

.scalablytyped

0.15

iven

0.14

wil

0.14

kah

0.14

ãĤ¡

0.14

#Region

0.14

ãĢĤãĢĤ↵↵

0.14

IVEN

0.13

Activations Density 0.070%

references to government or institutional support and collaborations

No Comments

No Known Activations