INDEX

Explanations

significant numeric values and references to processes or functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

izr

-0.16

ostel

-0.15

habi

-0.15

iffe

-0.15

umlu

-0.15

ebo

-0.15

izza

-0.14

ÃŃÅ¡

-0.14

hower

-0.14

oft

-0.14

POSITIVE LOGITS

 easily

0.15

æĸ¹

0.15

å¿«éĢŁ

0.15

 otherwise

0.15

 whilst

0.14

 easy

0.14

 Easily

0.14

 similarly

0.14

 ready

0.14

Activations Density 0.012%

significant numeric values and references to processes or functions

No Comments

No Known Activations