INDEX

Explanations

phrases indicating the presence of intriguing or noteworthy elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ummer

-0.17

assis

-0.16

 ìĸ¸ìłľ

-0.15

ī´

-0.14

_brightness

-0.14

Insets

-0.14

codegen

-0.14

uth

-0.14

xED

-0.14

iesz

-0.13

POSITIVE LOGITS

rb

0.16

pul

0.15

unky

0.14

ola

0.14

ory

0.14

 basal

0.14

 favor

0.14

 Feder

0.13

.opens

0.13

bis

0.13

Activations Density 0.020%

phrases indicating the presence of intriguing or noteworthy elements

No Comments

No Known Activations