INDEX

Explanations

occurrences of verbs indicating marking or labeling events or milestones

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

UB

-0.15

_subtype

-0.14

@$

-0.14

à¤§à¤°

-0.14

DAQ

-0.14

LC

-0.13

 shop

-0.13

ub

-0.13

annis

-0.13

POSITIVE LOGITS

 ÑģÐ¾Ð±Ð¾Ð¹

0.17

_Impl

0.16

ernel

0.15

pleted

0.14

 occasion

0.14

_literals

0.14

asant

0.14

bia

0.14

NOP

0.13

Activations Density 0.018%

occurrences of verbs indicating marking or labeling events or milestones

No Comments

No Known Activations