INDEX

Explanations

information regarding educational rankings and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

esis

-0.16

alker

-0.15

DataTask

-0.15

ãĥ³ãĥĪ

-0.15

alt

-0.15

ç¾©

-0.14

èª

-0.14

ese

-0.14

Jer

-0.14

å¯

-0.14

POSITIVE LOGITS

 Griffith

0.16

.record

0.15

ijkstra

0.15

rane

0.15

 topLeft

0.14

eydi

0.14

otch

0.14

 recur

0.13

ockey

0.13

 record

0.13

Activations Density 0.497%

information regarding educational rankings and achievements

No Comments

No Known Activations