INDEX

Explanations

expressions of critical and evaluative commentary in film or literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Halk

-0.18

thing

-0.16

odus

-0.15

 wedge

-0.14

 Hollow

-0.14

queues

-0.14

ENUM

-0.13

uddle

-0.13

ahoma

-0.13

åĮĸ

-0.13

POSITIVE LOGITS

atsapp

0.15

pill

0.15

ristol

0.15

upertino

0.14

ctest

0.14

udit

0.14

_SECURE

0.14

StackNavigator

0.14

uestion

0.14

sponsor

0.13

Activations Density 0.269%

expressions of critical and evaluative commentary in film or literature

No Comments

No Known Activations