INDEX

Explanations

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

NotAllowed

-0.17

eing

-0.15

KEN

-0.15

arence

-0.15

ãĥ³ãĥĨãĤ£

-0.15

eam

-0.15

 Lantern

-0.15

rous

-0.14

Bj

-0.14

 Cons

-0.14

POSITIVE LOGITS

 duro

0.16

mez

0.15

.AutoComplete

0.15

inet

0.14

ValueCollection

0.14

oco

0.14

orex

0.14

zos

0.14

lev

0.14

-full

0.14

Activations Density 0.027%

occurrences of the word "the"

No Comments

No Known Activations