INDEX

Explanations

terms related to "land" or geographic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÏĢÎ¿

-0.19

Ð·Ñĥ

-0.15

soles

-0.15

mach

-0.15

 Ð¼ÐµÑĢ

-0.15

fov

-0.14

(æľ¨

-0.14

BorderStyle

-0.14

.terminate

-0.14

\<^

-0.13

POSITIVE LOGITS

/as

0.15

essa

0.15

gren

0.15

power

0.14

ipe

0.14

 Romero

0.14

uria

0.14

owner

0.13

liness

0.13

Activations Density 0.010%

terms related to "land" or geographic references

No Comments

No Known Activations