INDEX

Explanations

elements related to assertion and evaluation in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

inox

-0.16

ENV

-0.15

itel

-0.14

kl

-0.14

quist

-0.14

 Smooth

-0.14

je

-0.14

agli

-0.14

anson

-0.14

omb

-0.14

POSITIVE LOGITS

rawer

0.20

 Exactly

0.17

 exactly

0.17

aticon

0.16

isan

0.15

ÙģØª

0.14

Exactly

0.14

actly

0.14

sic

0.14

 precisely

0.13

Activations Density 0.004%

elements related to assertion and evaluation in various contexts

No Comments

No Known Activations