INDEX

Explanations

phrases indicating hypothetical scenarios or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

orre

-0.15

UDA

-0.14

éĺħè¯»æ¬¡æķ°

-0.14

Î¹Ïĩ

-0.14

Ø±ÙĪÙĩ

-0.14

requete

-0.14

itched

-0.14

AccessException

-0.14

âĹİ

-0.14

emploi

-0.13

POSITIVE LOGITS

 suppose

0.52

 assume

0.49

say

0.47

Say

0.46

 Assume

0.44

assume

0.43

 imagine

0.42

Say

0.41

say

0.40

åģĩ

0.40

Activations Density 0.277%

phrases indicating hypothetical scenarios or examples

No Comments

No Known Activations