INDEX

Explanations

phrases related to ratings and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Mens

-0.15

Ã¢m

-0.14

 Statistical

-0.14

fet

-0.14

ongyang

-0.14

cheng

-0.14

ometric

-0.14

 Higgins

-0.14

 Stat

-0.14

nen

-0.14

POSITIVE LOGITS

 rating

0.16

/gpl

0.15

ÏģÎ¹Î¿

0.15

ãĥ¼ãĥĸ

0.15

Rating

0.14

border

0.14

ovit

0.14

Border

0.14

rant

0.13

ynth

0.13

Activations Density 0.020%

phrases related to ratings and evaluations

No Comments

No Known Activations