INDEX

Explanations

occurrences of the word "display" and its various forms in relation to showcasing items or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

/left

-0.15

leÅŁ

-0.15

Ð½Ð°Ð´

-0.15

ernels

-0.14

inally

-0.14

eros

-0.14

opers

-0.14

be

-0.14

icks

-0.14

NO

-0.14

POSITIVE LOGITS

agma

0.16

multiline

0.15

LEM

0.15

ees

0.15

HomeAsUpEnabled

0.15

_firestore

0.15

postcode

0.15

ENCIL

0.14

rael

0.14

ERCHANT

0.14

Activations Density 0.035%

occurrences of the word "display" and its various forms in relation to showcasing items or information

No Comments

No Known Activations