INDEX

Explanations

references to specific analytical frameworks and tools

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ð¾Ð¶

-0.18

gra

-0.16

yon

-0.15

illaume

-0.15

bbe

-0.14

 homo

-0.14

èĥ¡

-0.14

isky

-0.13

jen

-0.13

 make

-0.13

POSITIVE LOGITS

errer

0.15

aza

0.15

eres

0.15

ãĥĥãĥĪ

0.15

utow

0.14

 SPDX

0.14

esthes

0.14

Responder

0.14

anj

0.14

Activations Density 0.546%

references to specific analytical frameworks and tools

No Comments

No Known Activations