INDEX

Explanations

terms related to restoration and recovery

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

logan

-0.16

uckles

-0.15

still

-0.15

ilm

-0.15

 continued

-0.15

 SWITCH

-0.14

 Libre

-0.14

ÑĢÐµÑĪ

-0.14

 switch

-0.14

think

-0.14

POSITIVE LOGITS

 lost

0.28

 Lost

0.24

lost

0.21

Lost

0.20

 normal

0.18

 Ð²ÑĤÑĢÐ°

0.18

 original

0.18

 formerly

0.17

atural

0.17

 full

0.17

Activations Density 0.113%

terms related to restoration and recovery

No Comments

No Known Activations