INDEX

Explanations

statements expressing personal opinions or thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

emailer

-0.13

 bulundu

-0.13

ÙıÙĪØ§

-0.12

ãģ®ãģ¯

-0.12

ãģĵãģ¨ãģ§

-0.12

.pretty

-0.12

ellig

-0.12

anken

-0.12

ãĥ¼ãĥ«

-0.12

 Ð¿Ñĥ

-0.12

POSITIVE LOGITS

 there

1.20

there

0.98

 There

0.90

There

0.87

 THERE

0.85

 ÙĩÙĨØ§Ùĥ

0.72

 theres

0.60

 dort

0.51

.There

0.44

"There

0.43

Activations Density 0.906%

statements expressing personal opinions or thoughts

No Comments

No Known Activations