INDEX

Explanations

geographical locations and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ium

-0.16

pline

-0.16

ellen

-0.15

rescia

-0.14

 brake

-0.14

riel

-0.14

agh

-0.14

èĲ

-0.14

 bomb

-0.14

 Replay

-0.14

POSITIVE LOGITS

teb

0.17

Ð»Ð¸Ð·

0.16

uet

0.15

Ð¾ÑĢÑĤÑĥ

0.15

Æ°u

0.15

llib

0.15

 Cout

0.14

issan

0.14

[of

0.14

icket

0.14

Activations Density 0.104%

geographical locations and related terms

No Comments

No Known Activations