INDEX

Explanations

negative emotional experiences and difficult situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ussen

-0.16

//{{

-0.15

åį±

-0.14

.deepcopy

-0.14

azen

-0.14

lder

-0.14

à¤Ĥà¤¶

-0.14

Ð°ÑĤÐµÐ³Ð¾ÑĢ

-0.13

owa

-0.13

zos

-0.13

POSITIVE LOGITS

lest

0.25

 reality

0.24

 consequences

0.20

 truth

0.20

 reminder

0.20

 realities

0.19

 Reality

0.19

Reality

0.19

 truths

0.18

ly

0.18

Activations Density 0.182%

negative emotional experiences and difficult situations

No Comments

No Known Activations