INDEX

Explanations

programming-related syntax elements or functions

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

abox

-0.16

Ð°Ð

-0.15

NOP

-0.15

dit

-0.14

ikki

-0.14

wrap

-0.14

¢åįķ

-0.14

secutive

-0.13

box

-0.13

POSITIVE LOGITS

estar

0.16

appa

0.16

 Tout

0.15

ubs

0.14

 Vine

0.14

ritis

0.14

imm

0.14

ape

0.13

opathy

0.13

adam

0.13

Activations Density 0.002%

programming-related syntax elements or functions

No Comments

No Known Activations