INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

phans

-0.16

ato

-0.15

net

-0.14

ound

-0.14

rench

-0.14

atas

-0.14

Å¼e

-0.14

=YES

-0.14

 subtraction

-0.14

 ----------------------------------------------------------------------↵

-0.14

POSITIVE LOGITS

uzey

0.17

tle

0.16

irit

0.15

à¤ĵ

0.15

odes

0.14

ilan

0.14

oux

0.14

ÑĸÑģÑĤ

0.13

ahlen

0.13

vais

0.13

Activations Density 0.027%

No Comments

No Known Activations