INDEX

Explanations

interrogative punctuation and question marks

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

emer

-0.17

 seedu

-0.16

ingham

-0.16

/dr

-0.16

ifton

-0.15

ses

-0.15

side

-0.15

elsing

-0.15

licken

-0.15

keit

-0.15

POSITIVE LOGITS

rious

0.17

 Horton

0.15

ively

0.15

aneously

0.14

tings

0.14

groundColor

0.14

uating

0.14

 Ø·Ø±ÙĬÙĤ

0.14

ously

0.14

onne

0.14

Activations Density 0.030%

interrogative punctuation and question marks

No Comments

No Known Activations