INDEX

Explanations

terms related to injuries

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

statt

-0.16

ëľ

-0.15

ãĥ¼ãĥĵ

-0.15

idy

-0.15

aldi

-0.14

anou

-0.14

oning

-0.14

maj

-0.14

orro

-0.13

_dispatcher

-0.13

POSITIVE LOGITS

gaard

0.20

hes

0.17

asje

0.15

McD

0.14

itta

0.14

haf

0.14

omite

0.14

ASN

0.14

gree

0.14

Activations Density 0.007%

terms related to injuries

No Comments

No Known Activations