INDEX

Explanations

instances of references to tests, summaries, and recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

porto

-0.15

osto

-0.14

aldi

-0.14

 ...,

-0.14

 æĸ

-0.13

 Ð½Ð°ÑģÑĤ

-0.12

hooks

-0.12

anco

-0.12

iÃ§

-0.12

ystone

-0.12

POSITIVE LOGITS

-fontawesome

0.15

ÏĢÎ·

0.15

 Nack

0.14

licken

0.14

interp

0.14

 davon

0.14

 breakdown

0.13

esty

0.13

Uvs

0.13

 Dolphin

0.13

Activations Density 0.043%

instances of references to tests, summaries, and recommendations

No Comments

No Known Activations