INDEX

Explanations

instances of demonstrating behavior or examples of imitation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÏģÏİÎ½

-0.18

elper

-0.15

ayment

-0.15

Ð¾Ð²Ð°Ð½Ð¸Ð¹

-0.14

kont

-0.14

)frame

-0.14

_COMPAT

-0.14

_compat

-0.13

 getVersion

-0.13

irk

-0.13

POSITIVE LOGITS

ofs

0.15

umber

0.14

arters

0.14

ÑĢÐ¾Ð²Ð°

0.14

igos

0.14

ourn

0.14

 FixedUpdate

0.14

ÐĿÐ°Ñģ

0.14

.Copy

0.14

amodel

0.14

Activations Density 0.135%

instances of demonstrating behavior or examples of imitation in various contexts

No Comments

No Known Activations