INDEX

Explanations

specific names, locations, or references often associated with political or economic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 SPDX

-0.18

ÐµÐ¹Ð½

-0.16

çļĦæĺ¯

-0.15

iele

-0.14

/etc

-0.14

Î¯Î¶ÎµÎ¹

-0.14

LAR

-0.14

Ð»Ð°Ð´Ð°

-0.13

Overrides

-0.13

Mocks

-0.13

POSITIVE LOGITS

0.17

,to

0.16

empt

0.15

 FlatButton

0.14

,on

0.14

ãĥĲãĤ¹

0.14

Ã«l

0.13

ktor

0.13

thon

0.13

Activations Density 0.160%

specific names, locations, or references often associated with political or economic contexts

No Comments

No Known Activations