INDEX

Explanations

phrases that include the word "of."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Fallon

-0.19

asco

-0.15

radan

-0.15

orio

-0.15

azio

-0.14

AREST

-0.14

 æĺ

-0.14

 Newman

-0.13

 glitches

-0.13

 Torch

-0.13

POSITIVE LOGITS

Visualization

0.15

Subscriber

0.15

Sto

0.15

okrat

0.15

ierz

0.14

ertil

0.14

strar

0.14

ê³¡

0.14

undles

0.14

artin

0.14

Activations Density 0.094%

phrases that include the word "of."

No Comments

No Known Activations