INDEX

Explanations

quotation marks and their usage in text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ÑĥÑĪ

-0.16

Ã±ana

-0.15

ump

-0.15

 Roose

-0.15

ppo

-0.15

izabeth

-0.14

continent

-0.14

ardu

-0.14

 Hancock

-0.14

conexao

-0.14

POSITIVE LOGITS

rell

0.14

ady

0.14

ãģĤãĤĬãģĮ

0.14

ennen

0.14

URRENT

0.14

.ColumnHeader

0.14

_BLOCKS

0.14

ÐµÑĢÐ±

0.14

ÑĢÑĸÑĩ

0.13

iene

0.13

Activations Density 0.335%

quotation marks and their usage in text

No Comments

No Known Activations