INDEX

Explanations

phrases that indicate replacement or modification in contexts of composition or arrangement

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

tra

-0.17

het

-0.16

une

-0.15

acket

-0.14

ud

-0.14

uth

-0.14

uen

-0.14

assin

-0.14

ksen

-0.14

kie

-0.13

POSITIVE LOGITS

 WaitForSeconds

0.17

arsing

0.15

quito

0.14

agger

0.14

è¦

0.14

Eug

0.14

AlgorithmException

0.14

ãģ£ãģı

0.14

anych

0.13

ocoder

0.13

Activations Density 0.046%

phrases that indicate replacement or modification in contexts of composition or arrangement

No Comments

No Known Activations