INDEX

Explanations

references to participation and involvement in various activities or events

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

okie

-0.15

UPI

-0.15

gens

-0.14

 Ãľl

-0.14

.localized

-0.14

ocus

-0.14

.Inner

-0.14

å¤ķ

-0.14

vip

-0.14

ROTO

-0.14

POSITIVE LOGITS

tone

0.16

illian

0.14

 aged

0.14

 Burg

0.14

iona

0.13

erton

0.13

áº¡t

0.13

edBy

0.13

edException

0.13

arus

0.13

Activations Density 0.032%

references to participation and involvement in various activities or events

No Comments

No Known Activations