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

eyen

-0.16

ysl

-0.15

gos

-0.15

áº³ng

-0.15

ouver

-0.15

 Blonde

-0.14

obel

-0.14

Ð²Ð¾Ð»

-0.14

okit

-0.14

oksen

-0.14

POSITIVE LOGITS

 simultaneously

0.16

nto

0.15

alu

0.15

agues

0.15

eways

0.14

.Packet

0.14

iac

0.14

DoubleClick

0.14

.fast

0.13

_aspect

0.13

Activations Density 0.370%

No Comments

No Known Activations