INDEX

Explanations

code syntax structures, particularly around function definitions and class closures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

mob

-0.17

erc

-0.15

hrad

-0.15

phem

-0.15

aty

-0.15

quam

-0.15

mo

-0.14

deen

-0.14

pler

-0.14

VEC

-0.14

POSITIVE LOGITS

hausen

0.18

opper

0.17

BuilderInterface

0.15

 afterEach

0.15

 Marketable

0.15

ivals

0.15

ctl

0.14

ÅĻiv

0.14

ìĤ´

0.14

ahat

0.14

Activations Density 0.041%

code syntax structures, particularly around function definitions and class closures

No Comments

No Known Activations