INDEX

Explanations

names of individuals, particularly those associated with various groups or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

antino

-0.21

ctor

-0.19

orex

-0.17

ctic

-0.16

 Staples

-0.15

cter

-0.15

ekt

-0.14

ctors

-0.14

 Katz

-0.14

ereotype

-0.14

POSITIVE LOGITS

ataire

0.15

uelle

0.13

imeline

0.13

elled

0.13

Bom

0.13

ength

0.13

Cox

0.13

ä½ľçĶ¨

0.13

iddles

0.13

 Cabr

0.12

Activations Density 0.075%

names of individuals, particularly those associated with various groups or events

No Comments

No Known Activations