INDEX

Explanations

information about individuals and their roles or achievements

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

 Read

-0.16

thi

-0.14

iti

-0.14

XT

-0.14

xt

-0.14

EB

-0.14

NAT

-0.13

McB

-0.13

lect

-0.13

POSITIVE LOGITS

nnen

0.17

ennen

0.16

.scalablytyped

0.15

ì£¼

0.15

iferay

0.15

ActionCreators

0.15

OptionsResolver

0.14

lain

0.14

anoia

0.14

_ENCODE

0.14

Activations Density 1.074%

information about individuals and their roles or achievements

No Comments

No Known Activations