INDEX

Explanations

terms related to distinguishing or differentiating between entities or concepts

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

_elapsed

-0.14

ooth

-0.14

isode

-0.14

lets

-0.14

/Web

-0.13

ismu

-0.13

aska

-0.13

gorith

-0.13

YTE

-0.13

itsu

-0.13

POSITIVE LOGITS

 distinction

0.19

istingu

0.18

afil

0.16

iates

0.16

Ä±klÄ±

0.16

 distingu

0.14

iator

0.14

iating

0.14

 Param

0.14

ively

0.14

Activations Density 0.084%

terms related to distinguishing or differentiating between entities or concepts

No Comments

No Known Activations