INDEX

Explanations

components of proper noun phrases, particularly related to locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.16

Tib

-0.16

eryl

-0.15

lify

-0.15

arna

-0.14

unning

-0.14

æĭĶ

-0.14

 cast

-0.14

utches

-0.14

uffled

-0.13

POSITIVE LOGITS

bject

0.17

ODB

0.17

wart

0.15

elop

0.14

ignon

0.14

_TRAN

0.14

Ð°Ð¶

0.14

ãĥ©ãĤ¤ãĥ³

0.14

zag

0.14

adden

0.13

Activations Density 0.015%

components of proper noun phrases, particularly related to locations and entities

No Comments

No Known Activations