INDEX

Explanations

specific identifiers or names associated with people and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

aepernick

-0.17

zyst

-0.17

_gem

-0.16

Ð¾Ð³ÐµÐ½

-0.15

.Microsoft

-0.15

Yug

-0.15

ÅĻiv

-0.14

yon

-0.14

IRON

-0.14

anke

-0.14

POSITIVE LOGITS

 Pred

0.24

 Dark

0.23

Gor

0.23

 pred

0.21

Dam

0.21

Ves

0.19

 Milan

0.19

Bo

0.19

Dark

0.19

 Rank

0.19

Activations Density 0.012%

specific identifiers or names associated with people and events

No Comments

No Known Activations