INDEX

Explanations

proper nouns related to geographical locations or names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 dumpsters

-0.16

REA

-0.16

elor

-0.15

æŃ

-0.14

olo

-0.14

ji

-0.14

 here

-0.14

vd

-0.14

uler

-0.14

phin

-0.14

POSITIVE LOGITS

itan

0.16

ADDE

0.15

į

0.15

$__

0.15

erged

0.15

HDR

0.15

tera

0.14

ellen

0.14

IMIT

0.14

hort

0.14

Activations Density 0.058%

proper nouns related to geographical locations or names

No Comments

No Known Activations