INDEX

Explanations

specific numerical values and their implications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

urdu

-0.18

udge

-0.14

contr

-0.14

rsa

-0.14

kre

-0.14

.styleable

-0.13

bubble

-0.13

dcc

-0.13

ordan

-0.13

icies

-0.13

POSITIVE LOGITS

sko

0.15

aku

0.15

æĦ

0.14

opp

0.14

oud

0.14

arin

0.14

ades

0.13

ait

0.13

akis

0.13

ijn

0.13

Activations Density 0.033%

specific numerical values and their implications in various contexts

No Comments

No Known Activations