INDEX

Explanations

concepts related to organized actions or structured processes

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

ooth

-0.18

 Dias

-0.15

IOC

-0.15

-strokes

-0.15

ousse

-0.14

,{"

-0.14

rust

-0.14

 Chip

-0.14

drv

-0.14

Jam

-0.14

POSITIVE LOGITS

 colle

0.17

asonry

0.15

 Alam

0.14

isin

0.14

Col

0.14

::~

0.14

owell

0.14

col

0.14

umber

0.14

cem

0.13

Activations Density 0.034%

concepts related to organized actions or structured processes

No Comments

No Known Activations