INDEX

Explanations

phrases and questions related to the concept of causation or relevance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.16

 reins

-0.15

lassen

-0.15

rok

-0.15

gaard

-0.14

.getElementsBy

-0.14

_Impl

-0.13

mente

-0.13

crit

-0.13

POSITIVE LOGITS

edor

0.15

estro

0.15

adoo

0.15

CLR

0.14

irect

0.14

logic

0.14

 uncert

0.14

iedo

0.14

 Phelps

0.14

.direct

0.14

Activations Density 0.024%

phrases and questions related to the concept of causation or relevance

No Comments

No Known Activations