INDEX

Explanations

instances of the word "mode" and its variations in the context of technical or procedural descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

dale

-0.23

wood

-0.17

do

-0.17

ly

-0.17

nt

-0.17

roads

-0.17

land

-0.17

to

-0.16

eward

-0.16

ertia

-0.16

POSITIVE LOGITS

led

0.26

.Mode

0.21

hift

0.20

ONGL

0.20

(mode

0.19

ities

0.18

-mode

0.18

NotSupportedException

0.18

ality

0.17

 operand

0.17

Activations Density 0.032%

instances of the word "mode" and its variations in the context of technical or procedural descriptions

No Comments

No Known Activations