INDEX

Explanations

terms related to bias and measurement in a statistical or research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

\-

-0.14

bite

-0.14

boss

-0.13

Ð»ÑıÑħ

-0.13

 ÐľÐ¸Ñħ

-0.13

...</

-0.13

okie

-0.13

kud

-0.13

↵ ↵

-0.12

CEE

-0.12

POSITIVE LOGITS

 probably

0.19

 unmarried

0.18

 remodel

0.16

 seasons

0.15

probably

0.15

lease

0.15

 residences

0.15

 Probably

0.15

 lived

0.14

 enslaved

0.14

Activations Density 0.002%

terms related to bias and measurement in a statistical or research context

No Comments

No Known Activations