INDEX

Explanations

No Explanations Found

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

isor

-0.17

rane

-0.15

|int

-0.15

é¼»

-0.14

iani

-0.14

_DEFAULT

-0.14

ration

-0.14

ãĤ«ãĥĨãĤ´ãĥª

-0.14

nock

-0.13

åĢī

-0.13

POSITIVE LOGITS

utm

0.15

 Bench

0.15

geist

0.15

áº«n

0.14

áº«

0.14

roz

0.14

 unde

0.14

ÙģÙĨ

0.14

IGIN

0.14

tip

0.14

Activations Density 0.018%

No Comments

No Known Activations