INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

áº«

-0.15

imos

-0.14

 Tomorrow

-0.14

 Tail

-0.14

AILABLE

-0.13

ÑĤÐ¾Ð¼

-0.13

Ã¶l

-0.13

 nues

-0.13

ARAM

-0.13

geme

-0.13

POSITIVE LOGITS

rlen

0.17

idency

0.14

iddle

0.14

jun

0.14

åľĨ

0.14

akin

0.14

dea

0.13

 victim

0.13

umpy

0.13

oe

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.