INDEX

Explanations

references to accidents or injuries related to activities or conditions in various contexts

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

imes

-0.15

êµ

-0.14

Ð¾Ð³ÑĢÐ°ÑĦÑĸÑı

-0.14

å±±å¸Ĥ

-0.14

dma

-0.14

FormData

-0.14

omanip

-0.13

à¥ĩà¤ļ

-0.13

tie

-0.13

lfw

-0.13

POSITIVE LOGITS

 falls

1.08

 fall

1.08

 falling

1.06

 fallen

0.98

 fell

0.97

 FALL

0.97

fall

0.96

 Falls

0.91

 Fall

0.91

Fall

0.91

Activations Density 0.238%

references to accidents or injuries related to activities or conditions in various contexts

No Comments

No Known Activations