INDEX

Explanations

references to the act of writing and related skills

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

amento

-0.16

elsen

-0.16

uyen

-0.14

hit

-0.14

/mit

-0.14

STER

-0.14

 blanket

-0.14

sage

-0.13

amen

-0.13

POSITIVE LOGITS

.googleapis

0.18

offsetof

0.17

_DECLARE

0.16

xeb

0.16

æķ£

0.15

.getOwnPropertyDescriptor

0.14

zes

0.14

ëŁ

0.14

OffsetTable

0.14

adelphia

0.14

Activations Density 0.021%

references to the act of writing and related skills

No Comments

No Known Activations