INDEX

Explanations

references to guiding principles or authoritative sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

arily

-0.17

arr

-0.16

ikk

-0.16

kowski

-0.15

blood

-0.15

eenth

-0.15

iron

-0.14

ery

-0.14

ern

-0.14

 frank

-0.14

POSITIVE LOGITS

resher

0.18

luÅ¾

0.17

entes

0.16

Ymd

0.15

izes

0.15

ents

0.15

-worthy

0.15

ugar

0.14

ential

0.14

utable

0.14

Activations Density 0.060%

references to guiding principles or authoritative sources

No Comments

No Known Activations