INDEX

Explanations

phrases that indicate alternatives or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

arna

-0.17

ilo

-0.15

ÙĤØ¯Ø±

-0.14

ernes

-0.14

Ãªn

-0.14

ãĥ³ãĥĩ

-0.14

lessly

-0.14

POSITIVE LOGITS

 several

0.23

ific

0.20

 Bust

0.19

ignal

0.18

ifice

0.17

eres

0.17

few

0.16

Coder

0.16

-many

0.16

Ø¶

0.15

Activations Density 0.018%

phrases that indicate alternatives or choices

No Comments

No Known Activations