INDEX

Explanations

occurrences of the word "upon" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

poke

-0.17

idge

-0.16

runner

-0.15

room

-0.15

uces

-0.15

wyn

-0.15

aceous

-0.15

vice

-0.15

ening

-0.14

ubit

-0.14

POSITIVE LOGITS

 Upon

0.17

prav

0.17

Upon

0.17

 upon

0.16

orex

0.15

mw

0.14

à¸£

0.14

mol

0.14

assis

0.14

warts

0.14

Activations Density 0.028%

occurrences of the word "upon" and its variations

No Comments

No Known Activations