INDEX

Explanations

mentions of locations and route descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

iness

-0.16

ole

-0.15

fen

-0.15

uple

-0.15

rab

-0.14

arie

-0.14

rows

-0.14

rette

-0.14

fine

-0.13

zt

-0.13

POSITIVE LOGITS

ivec

0.15

edla

0.15

 Oliv

0.14

 learnt

0.13

.tc

0.13

 Lilly

0.13

 âĹĦ

0.13

/embed

0.13

ONGL

0.13

%+

0.13

Activations Density 0.006%

mentions of locations and route descriptions

No Comments

No Known Activations