INDEX

Explanations

references to citations and bibliographic sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

uan

-0.15

DECL

-0.15

ire

-0.14

 Mell

-0.14

.bc

-0.14

trak

-0.14

ordes

-0.14

imet

-0.13

ignet

-0.13

iji

-0.13

POSITIVE LOGITS

andum

0.18

âĢĮØ³ÛĮ

0.15

pin

0.14

SEA

0.14

eting

0.14

cura

0.13

ÏĢÎ¿Ïħ

0.13

nak

0.13

.getSession

0.13

 extr

0.13

Activations Density 0.007%

references to citations and bibliographic sources

No Comments

No Known Activations