INDEX

Explanations

references to specific institutions and their actions in relation to significant events or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

argent

-0.14

reib

-0.14

ëł´

-0.14

.wrap

-0.14

stagram

-0.13

Ã¤tz

-0.13

arga

-0.13

 smoothed

-0.13

inati

-0.13

kovÄĽ

-0.13

POSITIVE LOGITS

 suspend

0.22

 susp

0.21

 faced

0.19

 suspended

0.19

 suspension

0.19

Temp

0.17

 faces

0.16

 implement

0.16

 implemented

0.16

 apolog

0.16

Activations Density 0.175%

references to specific institutions and their actions in relation to significant events or decisions

No Comments

No Known Activations