INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

arcer

-0.15

zem

-0.14

íĬ

-0.13

ninger

-0.13

elf

-0.13

 GUIContent

-0.13

Unused

-0.13

Ð¾Ð±Ð°

-0.13

Ð¾Ð¾Ð±ÑĢÐ°Ð·

-0.13

quat

-0.13

POSITIVE LOGITS

ä¸Ķ

0.20

ISTA

0.16

(strict

0.16

erno

0.14

isex

0.13

 háº¡ng

0.13

istar

0.13

-only

0.13

 affair

0.13

 caucus

0.13

Activations Density 0.287%

No Comments

No Known Activations