INDEX

Explanations

occurrences of the word "ta" and its variations and uses

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

borg

-0.14

éĶ

-0.14

licit

-0.14

BUFFER

-0.14

éĮ

-0.14

Mil

-0.14

emer

-0.14

 Canonical

-0.14

PROTO

-0.14

portlet

-0.14

POSITIVE LOGITS

spo

0.20

akis

0.16

ooks

0.15

ASCADE

0.14

ucket

0.14

 Shack

0.14

oring

0.14

CID

0.13

 Bosch

0.13

Activations Density 0.009%

occurrences of the word "ta" and its variations and uses

No Comments

No Known Activations