INDEX

Explanations

phrases indicating recurring experiences or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.15

ellar

-0.15

onium

-0.15

jure

-0.14

ule

-0.14

 retire

-0.14

iÄħ

-0.14

£

-0.14

ium

-0.13

amy

-0.13

POSITIVE LOGITS

 been

0.18

<tag

0.14

forward

0.14

ask

0.14

 Been

0.14

Zem

0.14

odie

0.13

Ð¾Ð±ÑĢÐµÑĤ

0.13

holm

0.13

 graz

0.13

Activations Density 0.025%

phrases indicating recurring experiences or states of being

No Comments

No Known Activations