INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bidden

-0.14

abaj

-0.14

vip

-0.14

 Balk

-0.14

 sudden

-0.13

 infer

-0.13

.slim

-0.13

------+------+

-0.13

POSITIVE LOGITS

 presentation

0.15

Äįen

0.15

itch

0.15

uria

0.15

 presentations

0.15

iglia

0.15

fen

0.15

vice

0.14

Raz

0.14

issa

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.