INDEX

Explanations

elements related to coding or programming commands

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 subrange

-0.17

umm

-0.16

emet

-0.16

jom

-0.15

Ã¼lt

-0.14

overn

-0.14

klu

-0.14

missible

-0.14

iye

-0.14

.TabStop

-0.14

POSITIVE LOGITS

 Prompt

0.25

 prompt

0.24

aliases

0.24

 alias

0.24

 aliases

0.24

alias

0.24

_aliases

0.23

prompt

0.23

 Fish

0.23

 fish

0.22

Activations Density 0.009%

elements related to coding or programming commands

No Comments

No Known Activations