INDEX

Explanations

phrases that involve the word "they" and its variations, indicating a focus on actions or characteristics of multiple subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÄĻd

-0.15

lements

-0.14

)?$

-0.14

ìĤ´

-0.14

Å¼y

-0.14

Ã±as

-0.14

æ´²

-0.14

RESULTS

-0.13

erras

-0.13

.OnItemClickListener

-0.13

POSITIVE LOGITS

say

0.21

ingo

0.21

all

0.20

ebb

0.18

cord

0.17

atically

0.17

 call

0.17

 called

0.17

 both

0.17

 said

0.16

Activations Density 0.260%

phrases that involve the word "they" and its variations, indicating a focus on actions or characteristics of multiple subjects

No Comments

No Known Activations