INDEX

Explanations

phrases expressing beliefs or opinions about concepts

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

ton

-0.16

mons

-0.15

quette

-0.14

 gratuits

-0.14

planation

-0.14

indle

-0.14

tera

-0.14

ombs

-0.14

Interpreter

-0.14

interpreter

-0.13

POSITIVE LOGITS

oven

0.14

olit

0.14

Moh

0.14

olars

0.14

Moh

0.13

 Base

0.13

.MOUSE

0.13

 Advantage

0.13

sembled

0.13

fal

0.13

Activations Density 0.044%

phrases expressing beliefs or opinions about concepts

No Comments

No Known Activations