INDEX

Explanations

phrases or terms related to evidence and its significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

quist

-0.20

ish

-0.18

plevel

-0.17

nga

-0.16

ep

-0.16

stad

-0.15

ue

-0.15

egade

-0.15

isi

-0.15

sWith

-0.15

POSITIVE LOGITS

 base

0.23

-base

0.23

-based

0.22

 supporting

0.20

 Base

0.19

-Based

0.18

 linking

0.18

abase

0.18

tam

0.17

base

0.17

Activations Density 0.029%

phrases or terms related to evidence and its significance

No Comments

No Known Activations