INDEX

Explanations

time and date references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ìĹĩ

-0.15

éļİ

-0.15

Ð´ÐµÐ¼

-0.14

ecute

-0.14

Appear

-0.14

aub

-0.14

ENTE

-0.14

Nu

-0.14

anz

-0.13

glich

-0.13

POSITIVE LOGITS

Unnamed

0.17

event

0.16

.undefined

0.14

/event

0.14

ĥģ

0.14

insula

0.14

 spons

0.14

ÙĦØ§ØŃ

0.14

 event

0.13

iser

0.13

Activations Density 0.089%

time and date references

No Comments

No Known Activations