INDEX

Explanations

important nouns and phrases that indicate relationships or actions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

quo

-0.17

ÑģÑĤÐ¾Ñı

-0.17

hsi

-0.16

krom

-0.16

ilim

-0.15

paces

-0.15

æıı

-0.14

OTA

-0.14

_busy

-0.14

indo

-0.14

POSITIVE LOGITS

atri

0.16

rou

0.15

Dos

0.15

eden

0.15

.gb

0.14

UIT

0.14

eme

0.14

orton

0.14

aw

0.14

 MagicMock

0.14

Activations Density 0.001%

important nouns and phrases that indicate relationships or actions in various contexts

No Comments

No Known Activations