INDEX

Explanations

significant words and punctuation indicating philosophical or ethical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

zen

-0.16

atrice

-0.15

bah

-0.15

ensi

-0.15

aight

-0.14

omap

-0.14

bew

-0.14

leen

-0.14

tah

-0.14

POSITIVE LOGITS

peg

0.16

 ÏĢÎ±ÏģÎ¬

0.15

 Storm

0.14

igon

0.14

rels

0.14

 Strom

0.14

UPER

0.14

ayload

0.13

ich

0.13

.IsEmpty

0.13

Activations Density 0.000%

significant words and punctuation indicating philosophical or ethical concepts

No Comments

No Known Activations