INDEX

Explanations

occurrences of the prefix "re-", indicating repetition or return to a previous state or action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ifact

-0.16

anka

-0.15

andr

-0.15

ë§¨

-0.15

ouz

-0.14

hec

-0.14

fy

-0.14

atum

-0.14

ender

-0.14

 priv

-0.13

POSITIVE LOGITS

kind

0.22

inv

0.19

 kind

0.18

 charge

0.18

eling

0.17

 KIND

0.16

eled

0.16

 Hatch

0.16

Kind

0.16

 charges

0.16

Activations Density 0.034%

occurrences of the prefix "re-", indicating repetition or return to a previous state or action

No Comments

No Known Activations