INDEX

Explanations

mentions of specific entities, concepts, or situations related to assistance and improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Wo

-0.15

ienen

-0.14

emens

-0.14

 Rolling

-0.13

ordon

-0.13

aba

-0.13

::~

-0.13

 Toll

-0.13

 toll

-0.12

 Antoine

-0.12

POSITIVE LOGITS

vor

0.16

Mailer

0.15

Ð°ÑĢÐ°Ð¼

0.14

Ð¾ÑĤÑĮ

0.14

hound

0.14

ambda

0.14

_LOGGER

0.13

oka

0.13

.lt

0.13

ARGV

0.13

Activations Density 0.025%

mentions of specific entities, concepts, or situations related to assistance and improvement

No Comments

No Known Activations