INDEX

Explanations

references to monitoring, tracking, or commentary on events and entities in relation to media or narratives

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

asin

-0.16

ers

-0.16

eres

-0.15

ãĥ«ãĤ¯

-0.15

ssp

-0.15

ablo

-0.14

zym

-0.14

uctor

-0.14

 Preservation

-0.14

uncan

-0.14

POSITIVE LOGITS

-alist

0.15

 èµ·

0.15

isi

0.14

ishi

0.14

_DEFINED

0.14

_JOIN

0.14

oki

0.14

istr

0.13

{name

0.13

åĤ¬

0.13

Activations Density 0.142%

references to monitoring, tracking, or commentary on events and entities in relation to media or narratives

No Comments

No Known Activations