INDEX

Explanations

occurrences of the word 'W' along with various prepositions and conjunctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

bons

-0.15

as

-0.15

loff

-0.15

rava

-0.14

 repro

-0.14

ytt

-0.14

urls

-0.14

alls

-0.14

ksen

-0.14

POSITIVE LOGITS

abi

0.22

spin

0.20

 Indi

0.19

raz

0.19

roc

0.18

yr

0.18

ype

0.18

aha

0.18

cale

0.18

iel

0.18

Activations Density 0.019%

occurrences of the word 'W' along with various prepositions and conjunctions

No Comments

No Known Activations