INDEX

Explanations

structured data representations, particularly in log or error reporting formats

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

 absolut

-0.15

InlineData

-0.15

esel

-0.14

acic

-0.14

dto

-0.14

ãĥĩãĤ£ãĥ¼ãĤ¹

-0.13

 single

-0.13

Ð½Ð°Ð´

-0.13

 SINGLE

-0.13

Ð¾ÑģÑĮ

-0.13

POSITIVE LOGITS

_APPEND

0.14

 Giles

0.14

ÑĸÐ»ÑĮÑĪ

0.14

_depart

0.14

ÏģÎŃ

0.14

append

0.13

anne

0.13

aph

0.13

_HAVE

0.13

 binary

0.13

Activations Density 0.065%

structured data representations, particularly in log or error reporting formats

No Comments

No Known Activations