INDEX

Explanations

occurrences of the word "new" and similar variations in context to novelty or change

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

ingleton

-0.16

ety

-0.15

imson

-0.14

edith

-0.14

à¸¤

-0.14

EIF

-0.14

erty

-0.14

hipster

-0.14

å®ļ

-0.14

tight

-0.14

POSITIVE LOGITS

atak

0.17

ijd

0.16

utsch

0.14

 ngá»¯

0.14

rint

0.14

anian

0.14

 Niet

0.14

 sice

0.14

ILLA

0.14

 fare

0.14

Activations Density 0.001%

occurrences of the word "new" and similar variations in context to novelty or change

No Comments

No Known Activations