INDEX

Explanations

dates and temporal references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

CE

-0.17

hol

-0.16

 Bread

-0.15

 variety

-0.15

iska

-0.15

oy

-0.15

aight

-0.14

udi

-0.14

igham

-0.14

olar

-0.14

POSITIVE LOGITS

trys

0.17

neau

0.15

reeNode

0.15

ugas

0.15

seau

0.14

 /*#__

0.14

edom

0.14

slaught

0.14

rets

0.14

à¥Īà¤Ĺ

0.14

Activations Density 0.042%

dates and temporal references

No Comments

No Known Activations