INDEX

Explanations

phrases expressing beliefs or opinions about actions and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ju

-0.15

iju

-0.14

ensch

-0.14

amer

-0.14

 Juda

-0.13

pletion

-0.13

 Wald

-0.13

ä»®

-0.13

CanBe

-0.13

mlin

-0.13

POSITIVE LOGITS

0.17

 addCriterion

0.17

fy

0.17

_marshall

0.15

 Forge

0.15

ESA

0.15

itsu

0.14

later

0.14

wards

0.13

Activations Density 0.101%

phrases expressing beliefs or opinions about actions and consequences

No Comments

No Known Activations