INDEX

Explanations

technical terms related to software and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ers

-0.15

idia

-0.14

ubb

-0.14

ichert

-0.14

 Bers

-0.14

_skb

-0.14

ister

-0.14

 Ð·Ð´Ð°

-0.13

ec

-0.13

ppers

-0.13

POSITIVE LOGITS

defs

0.15

alse

0.15

ÅĤe

0.15

rait

0.15

Runtime

0.14

itm

0.14

Ð½Ð¸Ð²

0.14

ninger

0.14

.met

0.14

isce

0.14

Activations Density 0.046%

technical terms related to software and programming

No Comments

No Known Activations