INDEX

Explanations

terms that indicate evaluation or validation within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ãĥªãĤ«

-0.17

Neal

-0.15

drv

-0.14

 hmac

-0.14

Ã©o

-0.14

Î³ÎµÎ½

-0.14

ethyst

-0.14

vendor

-0.14

âĢĮØ³

-0.14

hci

-0.14

POSITIVE LOGITS

dos

0.17

 anytime

0.16

dz

0.15

å¶

0.15

dos

0.15

 dens

0.14

nier

0.14

rÃ³d

0.14

Activations Density 0.029%

terms that indicate evaluation or validation within various contexts

No Comments

No Known Activations