INDEX

Explanations

expressions indicating a specific point or stage within a process or journey

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

alez

-0.17

all

-0.17

ëĭī

-0.15

abit

-0.14

sid

-0.14

unger

-0.14

sian

-0.14

 UIApplication

-0.14

mund

-0.14

tery

-0.13

POSITIVE LOGITS

 through

0.17

 between

0.17

 into

0.15

ï»¿#

0.15

 House

0.15

erts

0.14

 toward

0.14

ÅĻaz

0.14

quat

0.14

riend

0.14

Activations Density 0.010%

expressions indicating a specific point or stage within a process or journey

No Comments

No Known Activations