INDEX

Explanations

pronouns indicating personal connection or group involvement

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

ãĥ¼ãĥĵ

-0.16

oad

-0.15

Ļ

-0.15

lder

-0.15

á»į

-0.14

 lantern

-0.14

 Lamp

-0.14

ÑĸÑĪ

-0.14

 uniform

-0.14

cao

-0.14

POSITIVE LOGITS

 tense

0.16

vez

0.16

 Reich

0.15

aned

0.14

subtract

0.14

æ¨¹

0.14

slashes

0.14

alara

0.14

CppClass

0.14

_RM

0.14

Activations Density 0.188%

pronouns indicating personal connection or group involvement

No Comments

No Known Activations