INDEX

Explanations

phrases that indicate beginnings, continuations, or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 continued

-0.22

 continuing

-0.21

continue

-0.20

 continue

-0.20

Continue

-0.20

continued

-0.19

 continues

-0.19

 Ð¿ÑĢÐ¾Ð´Ð¾Ð²Ð¶

-0.18

	continue

-0.17

 ê³ĦìĨį

-0.17

POSITIVE LOGITS

0.16

 Ð¿Ð¾Ð±Ð°

0.16

Rotor

0.15

 sembl

0.14

çľŁæŃ£

0.14

 seriously

0.14

 realized

0.14

otton

0.14

Activations Density 0.022%

phrases that indicate beginnings, continuations, or experiences

No Comments

No Known Activations