INDEX

Explanations

the presence of the name "Ne" and its variations, suggesting a focus on specific entities or references within the text

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

é¡

-0.17

ordable

-0.15

ree

-0.15

itesse

-0.15

 Fraser

-0.15

-0.14

inceton

-0.14

 Dickens

-0.14

rous

-0.14

 Comet

-0.14

POSITIVE LOGITS

ptune

0.19

Ne

0.17

/ne

0.17

Äįas

0.17

emiah

0.16

isser

0.16

CESS

0.16

esian

0.16

urope

0.16

umann

0.15

Activations Density 0.016%

the presence of the name "Ne" and its variations, suggesting a focus on specific entities or references within the text

No Comments

No Known Activations