INDEX

Explanations

references to the name "Poe."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

aris

-0.17

arus

-0.16

ëĿ

-0.14

/REC

-0.14

ukkan

-0.13

ode

-0.13

arah

-0.13

 Rough

-0.13

remen

-0.13

erus

-0.13

POSITIVE LOGITS

è¼ª

0.14

.localization

0.14

kia

0.14

usercontent

0.14

 æŃ£

0.14

ÐµÑĢÑĤÐ¸

0.14

strand

0.14

Arb

0.14

Ã¨m

0.13

razione

0.13

Activations Density 0.007%

references to the name "Poe."

No Comments

No Known Activations