INDEX

Explanations

references to durations and timeframes, particularly relating to years and months

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

esta

-0.17

sec

-0.15

isher

-0.15

olit

-0.14

aber

-0.14

atcher

-0.14

ythe

-0.14

 Patrol

-0.14

 overnight

-0.14

 patented

-0.14

POSITIVE LOGITS

_$

0.18

ä»½

0.16

ÐŁÐļ

0.16

/month

0.16

á»ĩu

0.15

itud

0.15

á»ĳt

0.14

à¸¸à¸ķ

0.14

ãĢħ

0.14

occan

0.14

Activations Density 0.048%

references to durations and timeframes, particularly relating to years and months

No Comments

No Known Activations